WO2007096876A2 - Return rate optimization system and method for promotions - Google Patents

Return rate optimization system and method for promotions Download PDF

Info

Publication number
WO2007096876A2
WO2007096876A2 PCT/IL2007/000234 IL2007000234W WO2007096876A2 WO 2007096876 A2 WO2007096876 A2 WO 2007096876A2 IL 2007000234 W IL2007000234 W IL 2007000234W WO 2007096876 A2 WO2007096876 A2 WO 2007096876A2
Authority
WO
WIPO (PCT)
Prior art keywords
data
promotion
customers
customer
graph
Prior art date
Application number
PCT/IL2007/000234
Other languages
French (fr)
Other versions
WO2007096876A3 (en
Inventor
Elad Inbar
Sephi Shapira
Original Assignee
Massive Impact International Limited
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Massive Impact International Limited filed Critical Massive Impact International Limited
Publication of WO2007096876A2 publication Critical patent/WO2007096876A2/en
Publication of WO2007096876A3 publication Critical patent/WO2007096876A3/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising

Definitions

  • the present invention relates to a return rate optimization system and method for promotions and, more particularly, but not exclusively to a system and method that allows a user to select an investment level in a promotion to achieve a predictable return.
  • IL2006/00402 published as WO2006/111952, teaches a customer discovery tool which allows a user to find potential customers from sparse data.
  • some of today's marketing activities and promotions may be targeted to a predefined group of potential customers.
  • Targeted promotions unlike random promotions, comprise a group of potential customers having common characteristics.
  • the targeted potential customers are chosen according to an estimate made by the promoters and the marketers based on characteristics that correspond to the typical purchaser of the promoted product or service.
  • targeted promotions the cost which is associated with sending numerous promotion offers is reduced.
  • the optimal mailing strategy depends on both the benefit obtained from a purchase and how the promotion offer affects the behavior of the potential customers.
  • the promoters aim to increase the response rate to each promotion by centering the promotion efforts on a group that has common external and demographic characteristics.
  • the promoters assume that external and demographic characteristics, such as gender, address and economic sector, reflect the customers' potential to purchase a promoted service or product. For example, a cellular content provider may chose a group of customer to promote a certain ringtone of a famous teenage rock star based upon the age of the group members.
  • the promoters ignore potential customers having other demographic characteristics. Untargeted customers who do not correspond with the chosen group may want to purchase the product for numerous unexpected reasons.
  • Another type of communication interaction is done without human intervention, such as an interaction with any computerized system via a communication network with an application server, including but not limited to billing systems, customer care systems, customer management systems, access to voicemail and other application servers, or roaming behavior of a cellular user.
  • the abundance of traceable network interactions allows the gatherer of the information to have the potential to elicit information about specific users.
  • customer-specific information can be used for personalized marketing, which is a form of product differentiation.
  • personalized marketing which is a form of product differentiation.
  • the abundance of traceable network interactions also presents many hurdles for the gatherers since they have to analyze huge amounts of data regarding numerous recorded interactions associated with numerous users.
  • Data mining is a technique by which hidden patterns may be found in a collection of data.
  • Contemporary data mining devices and modules do not just change the presentation of data, but actually discover previously unknown relationships among the data.
  • Data mining is typically implemented using a software agent.
  • the data mining software agent is added to a designated server in a database system and enables the analysis of the designated database records.
  • the software agent is implemented using designated hardware, which is connected to a computer network.
  • the software agent is used to analyze network interactions.
  • Data mining techniques are an effective and progressive tool for advertising and marketing systems. Such systems usually have to analyze an enormous amount of user information.
  • the user information comprises documented user network interactions and other user related information which is constantly gathered.
  • the user related information comprises demographic information, average monthly bills, habits and other information regarding the user.
  • U.S. Patent No. 6,968,3105 Another example for personalized advertising based upon data mining techniques is disclosed in U.S. Patent No. 6,968,315, issued on November 22, 2005.
  • the patent relates to advertising over a communications network comprising a plurality of interactive client subscriber sites interconnected with an advertising information server site.
  • the attributes of a plurality of customers are stored in the form of customer attribute vectors.
  • the patent uses a marketing function which maps the customer attribute vectors to one or more role model attribute vectors.
  • interactive advertising displays are provided incorporating the one or more role models.
  • the customer discovery tool gains knowledge of each promotion and, hence is used to generate a more productive and focused target list for subsequent promotions.
  • the ability to utilize the advantages of empirically-gathered quantitative information of customers' reactions to promotions leads to improved targeting of clientele.
  • the customer discovery tool provides a targeting system that can examine sparsely existing information regarding user behavior patterns during long time periods and analyze the feedback to promotions during marketing processes that comprise more than one promotion iteration.
  • the tool improves the quality of the network interaction analysis by including the analysis of user network interactions in a number of conscious or unconscious communication networks and combination of information which has been obtained from different sources.
  • the tool also utilizes the information that can be extracted from different network interactions that each user consciously or unconsciously performs with applications and servers regarding the feedback the user has given to previous promotions.
  • the tool also manages to utilize hyper sparse data from previous promotions to generate a new promotion.
  • the customer discovery tool yields a list of potential customers targeted for promotion by combining data mining models, genetics algorithms, natural selection algorithms, pattern recognition algorithms, prediction algorithms and the like, based on any documented communication action or interaction a potential consumer may perform, inter alia: sending or receiving a Short Message Service (SMS), a Multimedia Messaging Service (MMS), an Enhanced Messaging Service (EMS), a phone call, or an IVR call. In addition, this may include switching between different SMS (SMS), a Multimedia Messaging Service (MMS), an Enhanced Messaging Service (EMS), a phone call, or an IVR call. In addition, this may include switching between different
  • WEB pages or television channels connecting to a specific wireless or wired network, using a satellite or cable receiver, reacting to an Interactive Voice Response (IVR), accessing e-mail and text-based WebPages using a mobile phone, and any other form of recordable interaction that a potential consumer can do consciously or unconsciously with any system or communication network or application server as recorded over the online world.
  • IVR Interactive Voice Response
  • the customer discovery tool teaches targeting of marketing activity based on empirical customer reaction data as opposed to known marketing methods, known marketing assumptions and traditional surveys. Such an approach may be referred to as empirical marketing, and is herein called customer discovery.
  • the operator may empirically predict the likelihood that a specific interaction with a customer will result in a specific action.
  • the customer discovery tool deals with empirical data related to numerous individual customers, the sheer quantity of data makes it hard for a user to interact therewith and make decisions based on a reasonable analysis.
  • the tool enables the discovery of potential customers. New and existing customers are identified as potential customers for offerings of products and services. Preferably, the tool identifies and targets potential customers identifies and allows a group of customers to be chosen for specific promotions in order to achieve the highest return on investment (ROI), by calculating a parameter such as the return time factor.
  • ROI return on investment
  • the act of choosing is difficult since the body of data is so large.
  • the tool may empirically examine the characteristics of customers who have responded to different promotions. But again, due to the quantity of data it is difficult to take the next step and generate a new targeted promotion based upon the common characteristics of those responding customers.
  • the potential consumers are offered promotions that match their specific needs and interests.
  • the tool for identifying and targeting potential customers can address aspects in both the personal life and professional life of potential customers provided that the data management issues can be addressed.
  • the tool has the ability to collect customer related information and to extract habits and fields-of-interest data about different potential customers therefrom.
  • the tool has the ability to collect and analyze information about the reactions of potential consumers to products and services that the potential consumers have taken an interest in during previous promotions.
  • Information about the preferences of potential customers are extracted by the tool from various network interactions.
  • the network interactions which can be monitored originate from various sources such as, for example, cellular service servers, ISP service servers, PSTN central server, etc.
  • the gathered customer related information is used to generate an empirical decision regarding the suitability of the customer to a certain promotion.
  • the physical meaning which is represented in the gathered customer related information is not analyzed.
  • the tool does not differentiate between different customer related information by preferring one piece of information over the other. For example, customer related information regarding the age of the client is equally valued as customer related information regarding the customer SMS communication habits.
  • the physical meaning which is represented by the customer related information is not analyzed or valued during the promotion generation process.
  • the customer discovery tool and like systems thus lack an intuitive way of presenting the large quantity of data acquired to allow rapid and correct decisions to be made.
  • a method of providing an efficient promotion based on an analysis of a previous promotion comprising: analysing data of the previous promotion to discover likely customers based on response to the previous promotion, transferring said analysis data onto a graph indicating cost of reaching a given number of customers against overall response rate, from said graph selecting a point, said point defining a certain cost and a certain response rate, and feeding said data back to a list of customers to target customers based on likely response rate from clusters giving a highest response rate downwards until said point is reached.
  • an interface device for allowing a user to interface with cumulative data in order to set parameters in respect thereof, comprising: a data input for accepting data being cumulative along a first axis; a calculation tool for calculation of values associated with said cumulative data for a second axis; a plotting tool for plotting said cumulative data against said first and second axes to form a graph; and a response input for receiving a user input defining a location on said graph, therefrom to define parameters for said cumulative data based on said location; said parameters being output by said interface device.
  • apparatus for obtaining parameters for a promotion based on data obtained from a previous promotion comprising: a data analysis unit configured for analyzing data of the previous promotion to generate graph points; a data presentation unit configured for presenting said graph points as an interactive interface, said interactive interface being capable of receiving a user reaction; and a interface analysis unit configured for analyzing said user reaction in terms of graph points local to the user reaction and providing recommended parameters for a future promotion.
  • Implementation of the method and system of the present invention involves performing or completing certain selected tasks or steps manually, automatically, or a combination thereof.
  • several selected steps could be implemented by hardware or by software on any operating system of any firmware or a combination thereof.
  • selected steps of the invention could be implemented as a chip or a circuit.
  • selected steps of the invention could be implemented as a plurality of software instructions being executed by a computer using any suitable operating system.
  • selected steps of the method and system of the invention could be described as being performed by a data processor, such as a computing platform for executing a plurality of instructions.
  • Fig. 1 is a simplified block diagram illustrating a first preferred embodiment of the present invention for selecting parameters for a promotion based on interpretation of data from a previous promotion.
  • Fig. 2 is a simplified block diagrams showing data flow through a system for selecting parameters for a promotion based on interpretation of data from a previous promotion, according to a preferred embodiment of the present invention.
  • Fig. 3 is a simplified flow chart showing operation of a method selecting parameters for a promotion based on interpretation of data from a previous promotion, according to a preferred embodiment of the present invention.
  • Fig. 4 is a simplified diagram showing an interface according to a first preferred embodiment of the present invention based on a three-axis graph.
  • Fig. 5 is a simplified block diagram illustrating units of a system according to the preferred embodiments of the present invention.
  • Figs. 6 - 10 are simplified schematic diagrams showing how multiple promotions can be efficiently targeted at the same group of customers according to preferred embodiments of the present invention.
  • the present embodiments comprise a system and method that integrates relevant information, for example data obtained through the customer discover tool referred to in the background into a single user interface that allows a business user to make an informed decision.
  • the user is provided with an interface that allows parameters to be set for future activity based on the obtained data from the previous activity.
  • the previous activity may be a promotion and the data obtained may be customer discovery data.
  • the interface may use data of identified customers to show how a new campaign can be effectively targeted and show trade-offs in resources used against projected response rate.
  • a decision may then be made concerning the parameters to be used in a future promotion.
  • the power of the interface to help in decision making may help a business user to optimize the resources of his organization, thus to maximize the profits and to avoid a potential loss to his organization.
  • the service response model provides a tool for a user to make the appropriate economic decision under the constraints of his organization. More generally, the system provides an interface for making decisions based on cumulative data. The cumulative data is presented as a graph so that rates of change are apparent and the user can then choose a decision point from the graph. The decision point is translated into parameters which are then used in making selections based on the original data.
  • - User or User identifier is either a mobile user obtained by his unique MSISDN or any other unique identifier for a specific user. Such mobile users may be potential customers for a promotion targeted over the mobile network.
  • Any promotion including content promotion, advertising, registration invitation, churn management promotion, price plan promotion or any other form of message that may be delivered to a potential customer by any method (e.g. SMS, MMS, email, Print, mail, internet advertisement etc.)
  • Recall rate the percentage of potential customers the promotion is to attain. 100% recall means 100% of potential market size.
  • Promotion size the number of potential customers that are to be targeted with the promotion
  • Response rate the number of potential customers that respond to the promotion relative to the promotion size.
  • Target point represents a feasible combination of response rate, recall rate and promotion size.
  • Operator an operator, including an organization, wishing to run a promotion, also referred to as a promoter.
  • Fig. 1 shows apparatus for obtaining parameters for a promotion based on data obtained from a previous promotion.
  • the apparatus 10 makes use of a customer discovery tool 12 which obtains data from an existing promotion.
  • the customer discovery tool preferably includes customer data and customer profiles.
  • the tool provides details of those customers who actually responded to the earlier promotion.
  • the customers who responded can be mapped on a plane, based on their profile information, and data mining models, natural selection and genetic algorithms may then be used to find where the responding customers cluster on the map and which other customers fit the profiles of the clusters and can therefore also be identified as potential customers.
  • the actual customers together with potential customers that cluster with the actual customers may then be used to form new promotion lists.
  • the customer discovery tool includes a discovery unit 14 for empirically analyzing customer data regarding customer reaction to the earlier promotion.
  • the analysis identifies groupings or clusters of customers differentiated by the reactions, meaning those who responded in some way to the promotion.
  • a targeting unit, 16 targets customers belonging to the groups discovered from customers showing correlated reactions during the analysis stage.
  • the discovery tool thus yields a list of potential customers targeted for promotion by combining data mining models, genetics algorithms, natural selection algorithms, pattern recognition algorithms, prediction algorithms and the like, based on any documented communication action or interaction a potential consumer may perform, inter alia: sending or receiving a Short Message Service (SMS), a Multimedia Messaging Service (MMS), an Enhanced Messaging Service (EMS), a phone call, or an IVR call.
  • SMS Short Message Service
  • MMS Multimedia Messaging Service
  • EMS Enhanced Messaging Service
  • phone call or an IVR call.
  • this may include switching between different WEB pages or television channels, connecting to a specific wireless or wired network, using a satellite or cable receiver, reacting to an Interactive Voice Response (IVR), accessing e-mail and text-based WebPages using a mobile phone, and any other form of recordable interaction that a potential consumer can do consciously or unconsciously with any system or communication network or application server as recorded over the online world.
  • IVR Interactive Voice Response
  • customer discovery tool 12 carries out targeting of marketing activity based on actual customer data, as opposed to traditional marketing methods, known marketing assumptions and traditional surveys. Such an approach may be referred to as empirical marketing, and is herein called customer discovery.
  • the customer discovery tool may discern certain customers who responded very easily to a basic promotion, and others who took longer, or who required more promotion until they responded. That is to say, the customer discovery tool in fact finds out more about the potential customer than merely binary information about his likelihood to respond.
  • the customer discovery data is provided through API 18 to customer - point analyzer 20.
  • customer - point analyzer 20 In general it is possible to analyze the data, and the customers within the data, to define a cost or difficulty in obtaining a response from a given customer, so that the customers can be ordered in terms of ease in getting a response. Certain customers are presumably easy to reach and influence, and others are presumably difficult to reach and influence.
  • the customer - point analyzer uses the above presumptions to order the customer data into data points, each of which is a cumulative number of customers achieved for a certain amount of promotional effort.
  • the points are passed to interface unit 22 which draws them as a graph, as per Fig. 4, which will be described in greater detail below.
  • the graph shows the number of customers that can be reached by a promotion against the effort put into reaching them.
  • the axes of the graph can be labeled with quantifiers thus to give a cost of reaching a given number of customers etc.
  • the user can then provide input to the graph to provide parameters to define a particular promotion. For example he can press on a particular point on the graph to define a given level of effort in an upcoming promotion based on the predicted success rate.
  • the result of the user interaction is to provide one or more parameters, which can now be used to define a promotion.
  • the parameters are now fed back to the customer discover tool 12 so that the new parameters can be superimposed on the customers in the tool.
  • Using the parameters a list of suitable customers can be created and then targeted by the promotion using the targeting unit 16.
  • FIG. 2 is a simplified diagram illustrating a flow of data according to a preferred embodiment of the present invention. Ovals represent data and rectangles represent processing entities.
  • Data 30 of the customers is available from the customer discovery tool 12.
  • a data analysis unit, 32 in effect the customer to point analyzer, creates data points 34, typically cumulative.
  • the data points 34 are arranged into a graph 36 by data presentation unit or interface 38.
  • An interface analysis unit 40 then reads a user interaction 37 with the graph 36 in terms of graph points local to the user reaction, and produces one or more parameters 42 which are then fed back to the individual customers in the customer discovery tool, as recommendations for a future promotion.
  • Graph 36 is preferably provided as a three-axis graph, as will be described in greater detail below.
  • one axis is an independent axis and the remaining axes are interdependent on each other, for example having a crossed values relationship.
  • the top and the bottom axis have a crossed values relationship. That is to say the bottom axis goes from left to right while the upper axis goes from right to left.
  • the values on each axis are not independent of the other.
  • the top value may define or affect the bottom value and vice versa.
  • the data presentation unit or interface 38 inserts a point beyond which the cost of reaching an additional customer exceeds the intrinsic value of a customer in the promotion. That is to say the graph indicates the economic limitations that apply to the promotion. Other forms of unfeasibility may also be marked on the graph. For example a promotion may be limited by infrastructure availability. Certain levels of promotion may be prohibited by the limitations of the available bandwidth.
  • the data points 34 may comprise data such as a response rate at that point on the graph, a number of promotional contacts, and a cumulative or absolute number of responses to that point, or any other information that is believed to be useful.
  • the minimum promotion size and cost of promotion may specifically be dependent on selection by the customer interaction.
  • FIG. 3 is a simplified flow diagram illustrating a method of providing an efficient promotion based on an analysis of a previous promotion.
  • the method comprises stages of:
  • Fig. 4 is a simplified diagram illustrating the graph 36 at the center of the user interface 38 of the presently preferred embodiments.
  • the user interface 38 of the present embodiments may provide a graph with three axes, each axis being a domain affecting the decision to be made on the promotion.
  • the three axes may be:
  • the interface summarizes the information available regarding the promotion in such a way loss of information is minimized or avoided.
  • the graph may clearly mark, visually, any non-economical target points, as explained.
  • the system receives all relevant information for a given promotion and presents it in such a way that a user can make a decision and input that decision with the click of a mouse. With a single click a new promotion can be defined and launched.
  • the system Upon opening the user interface, the system loads the target points and any economic restrictions, such as minimum required response rate.
  • the information is supplied by the operator and displayed in the information provider.
  • the information may be obtained by the user in any way desired.
  • the system analyzes feasible target points extracted from the existing data and creates a new set of target points.
  • the new set contains the same information as the original set, but consists of only enough target points for a readable presentation of the information - The manageable information set.
  • the system plots the manageable information set on a three axes graph.
  • the bottom axis shows the promotion target group size.
  • the left axis shows the total expected users.
  • the top axis shows the response rate.
  • Each point on the graph is a possible (but not necessarily realistic) target point.
  • the system marks in one way, say using a red circle, all the feasible target points with response rate lower then the required minimum response rate as provided by the business user. These points reflect promotions that are feasible in the sense that the could be carried out, but which may not produce an economic return, that is to say the organization might experience economic loss.
  • the system marks in another way, say in yellow, all target points that are not attainable because of technical system constraints. For example, the system might not be able to deliver such a large number of video messages on time due to lack of system capacity, for example lack of available network bandwidth etc, or a promotion involving personalized messages to customers may be limited by organizational bandwidth in preparing the personalized messages.
  • the business user selects the desired target point by clicking a point on the graph.
  • the system knows the cost of each promotional message, and the profit from a positive response.
  • the system also knows the response rate over any given group of customers, so that a given point can be categorized as economical or non-economical. If the business user selects a non-economical target point; the system preferably issues a warning.
  • a summary of economic and statistical implications of the selected target point are presented to the business user for confirmation.
  • the summary preferably includes the following:
  • the system provides a notification regarding the creation of a target group of customers with a certain expected response rate, recall rate and promotion group size.
  • the target group then receives the promotion.
  • FIG. 4 An analysis of the graph in Fig. 4 shows three regions, a steep initial region, where a small increase in promotion size leads to a large increase in customers, an intermediate region with a falling curve where the effectiveness of the promotion gradually reduces and a relatively flat final region where large additional increases in effort bring in very few additional customers.
  • a promoter would normally be expected to include the initial region in his promotion and exclude the final region, using his judgment as to where in the intermediate region to end the promotion.
  • the system operation includes the following steps:
  • the information collection may involve an information provider and the user of the promotions.
  • the data may be collected using the customer discovery tool 12 as explained above, but other sources may be used as well or instead.
  • the system converts the information set including target points to a manageable set for presentation purposes, as explained above. For example data points based on each individual customer may be merged into combined data points representing a hundred customers.
  • the system presents the feasible target point on a three axis graph, such as that of Fig. 4.
  • Indications and warnings are provided for possible non-economical decisions - for example target points in which the total expected costs exceed the total expected revenue from a promotion, as explained.
  • the point defines the parameters of the promotion according to the three axes, so that the user effectively selects a target group for a specific promotion.
  • the parameters ensure that the promotion is aimed to meet the promoter's organization goals. If the user selects a non-economic point, a warning may be issued.
  • the system presents a summary of economic and statistical implications of the selected target point.
  • the system notifies a back-end system on the creation of a target group with the specified response rate, promotion size and potential positive responses.
  • the customers to be included in the target group are preferably available from the customer discovery tool.
  • Fig. 5 illustrates the interfacing system as a series of modules, an information receiver module 60, a transformation module 62 and a notification module 64.
  • the information receiver module 60 is an interface between the back-end system and the service response model, and is designed to obtain all possible points which could easily be numbered in the tens or hundreds, and also obtain or calculate the data values which go with each one of them, as well as all the promotion specific metrics such as minimum response rate for ROI, cost of 1 promotion, value of response.
  • the module runs sanity checks on the data, and then the data, including the target points and business restrictions into the transformation model.
  • the transformation module 62 transforms the information received from the information receiver module as target points, to a manageable sized set of target points. Also, the transformation module flags the target points which have a response rate above the minimum required response rate. The transformation module selects some of the reduced number of points, say around ten, based on business logic to mark as providing maximum profit, or maximum profit in a given region, and marks bad or non-profitable and otherwise unattainable points as discussed above. The end result is displayed to form the interactive user interface.
  • the transformation module thus produces the data that is used directly in the graph of Fig. 4.
  • the notification module 64 produces messages. As the promoter clicks on a target point on the service response model graph, the notification module notifies the back-end system regarding the request so that creation of a target group can be carried out with the selected parameters from the three axes: promotion size, response rate and recall rate corresponding to the target point. That is to say, once the operator selects a point on the graph, the notification module translates the selected point, say point no. 6, into the real values behind it, that is a number of promotions to send, response rate etc, and these values are then transmitted as parameters back into the customer discovery system for the generation of the customer list for the promotion.
  • the graph used in the interface may be varied.
  • the upper axis currently the response rate axis, can hold different parameters such as: • Money - how much money any given point on the graph produces.
  • FIG. 6 is a simplified diagram illustrating in schematic form a series of three promotions as they might be targeted at the same group of customers.
  • graph 70 shows three different possible promotions for ringtones, which it is intended to market to the same overall group of potential customers based on response rates to previous promotions.
  • Each promotion is for ringtones and is aimed at users who have shown interest in ringtones, but not all customers seem to be responsive to the same marketing techniques, and the question is one of launching the three promotions independently or somehow merging them.
  • Each promotion has a value marked thereon, which is the number of potential users multiplied by the response rate.
  • Fig. 7 in which the freering and four ring promotions are selected for merging.
  • the freering promotion has a value of $8k and the four ring promotion has a value of $ 13k.
  • Fig. 8 shows the three promotions 72, 74 and 76 following the merger between promotions 74 and 76.
  • the total value is now 16k which is not the sum of the two original promotions. Neither is the total number of potential customers the sum of the individual promotions. The reason for the discrepancy is that many of the potential customers for the two promotions are the same. For each common customer it is then determined which of the two promotions gives a higher value. For example if in the freering promotion the customer has a 30% chance of paying $5, giving a total value of $1.50, and in the four ring promotion the same customer has a 73 chance of paying $3, giving a total of $2.19, then it is more efficient to target this user with the four ring promotion than with the freering promotion. Thus such a customer would be targeted with the four ring promotion.
  • Fig. 9 shows the selection of the two ring promotion for marking with the merged four ring and freering promotions.
  • Fig. 10 shows the result of the merging.
  • the interface of Fig. 4 can be used to define the size of a given promotion before merging is carried out. However preferably the interface is used to select the final resources put into the merged promotion.

Abstract

Apparatus obtains parameters for a promotion based on data obtained from a previous promotion. The apparatus includes a data analysis unit for analyzing data of the previous promotion to generate cumulative graph points, a data presentation unit which presents the graph points as an interactive interface, to receive a user reaction; and an interface analysis unit which analyzes the user reaction in terms of graph points local to the user reaction and provides recommended parameters for a future promotion.

Description

RETURN RATE OPTIMIZATION SYSTEM AND METHOD FOR PROMOTIONS
FIELD AND BACKGROUND OF THE INVENTION The present invention relates to a return rate optimization system and method for promotions and, more particularly, but not exclusively to a system and method that allows a user to select an investment level in a promotion to achieve a predictable return.
IL2006/00402, published as WO2006/111952, teaches a customer discovery tool which allows a user to find potential customers from sparse data. As commonly known, some of today's marketing activities and promotions may be targeted to a predefined group of potential customers. Targeted promotions, unlike random promotions, comprise a group of potential customers having common characteristics. The targeted potential customers are chosen according to an estimate made by the promoters and the marketers based on characteristics that correspond to the typical purchaser of the promoted product or service. By using targeted promotions, the cost which is associated with sending numerous promotion offers is reduced. The optimal mailing strategy depends on both the benefit obtained from a purchase and how the promotion offer affects the behavior of the potential customers.
By using targeted promotion, the promoters aim to increase the response rate to each promotion by centering the promotion efforts on a group that has common external and demographic characteristics. The promoters assume that external and demographic characteristics, such as gender, address and economic sector, reflect the customers' potential to purchase a promoted service or product. For example, a cellular content provider may chose a group of customer to promote a certain ringtone of a famous teenage rock star based upon the age of the group members. However, by electing potential customers to promote according to external and demographic characteristics, the promoters ignore potential customers having other demographic characteristics. Untargeted customers who do not correspond with the chosen group may want to purchase the product for numerous unexpected reasons. Moreover, since the potential customers are analyzed according to their external and demographic characteristics, no empiric evaluation of their reaction to previous promotions is calculated. Progress in communication network technologies enables a promoter to accumulate ever more information about potential costumers. Network interactions are constantly performed for personal communication and commercial activity. One type of communication interaction is initiated by a specific user, and includes sending an SMS or an MMS, participating in a phone conversation, WEB surfing, etc.
Another type of communication interaction is done without human intervention, such as an interaction with any computerized system via a communication network with an application server, including but not limited to billing systems, customer care systems, customer management systems, access to voicemail and other application servers, or roaming behavior of a cellular user.
Since each user performs numerous traceable network interactions over various networks, the amount of information that can be accumulated about each user is substantial.
The abundance of traceable network interactions allows the gatherer of the information to have the potential to elicit information about specific users. Such customer-specific information can be used for personalized marketing, which is a form of product differentiation. By analyzing information about the clients, the marketer or the advertiser tries to make a unique product offering for each customer. However, the abundance of traceable network interactions also presents many hurdles for the gatherers since they have to analyze huge amounts of data regarding numerous recorded interactions associated with numerous users.
In order to, inter alia, enable the analysis of an abundance of recorded information, data mining techniques and methods have been developed over recent years. Data mining is a technique by which hidden patterns may be found in a collection of data.
Contemporary data mining devices and modules do not just change the presentation of data, but actually discover previously unknown relationships among the data. Data mining is typically implemented using a software agent. Usually, the data mining software agent is added to a designated server in a database system and enables the analysis of the designated database records. In another data mining model, the software agent is implemented using designated hardware, which is connected to a computer network. In the aforementioned computer network model, the software agent is used to analyze network interactions. Data mining techniques are an effective and progressive tool for advertising and marketing systems. Such systems usually have to analyze an enormous amount of user information. The user information comprises documented user network interactions and other user related information which is constantly gathered. The user related information comprises demographic information, average monthly bills, habits and other information regarding the user.
Using the data mining modules and other analytic tools, advertisers and marketers can provide a unique product and service for each customer according to his profile and usage history. An example of a system that enables selected advertising or marketing content based on each user's profile and usage history is disclosed in U.S. Patent No. 6,847,969, issued on January 25, 2005, which discloses a personalized advertising system for providing personalized and integrated online services for communications and commercial transactions both in private and public spaces. The disclosure also provides advertisers with the opportunity to directly engage actual and potential user- consumers with selected advertising or marketing content based on each user's profile and usage history.
Another example for personalized advertising based upon data mining techniques is disclosed in U.S. Patent No. 6,968,315, issued on November 22, 2005. The patent relates to advertising over a communications network comprising a plurality of interactive client subscriber sites interconnected with an advertising information server site. The attributes of a plurality of customers are stored in the form of customer attribute vectors. The patent uses a marketing function which maps the customer attribute vectors to one or more role model attribute vectors. At the interface advertising information server site, interactive advertising displays are provided incorporating the one or more role models.
Notwithstanding the aforementioned, currently known targeting systems fail to support or inadequately support the analysis of sporadic and sparse data which has been gathered from various network interactions of probed users and do not combine information regarding the same user from various sources, hence the customer discovery tool referred to above, which is designed to work with such sparse data. The customer discovery tool empirically analyzes the behavior of the users. The prior targeting systems analyze consumer related information which has been previously gathered by servers of different service providers. However, the known targeting systems do not probe or analyze the reactions of customers to their promotions. The analysis is usually passive, and does not integrate a learning mechanism that enables a more suitable promotion. The customer discovery tool by contrast does analyze reactions of the customers to an actual promotion.
The customer discovery tool gains knowledge of each promotion and, hence is used to generate a more productive and focused target list for subsequent promotions. The ability to utilize the advantages of empirically-gathered quantitative information of customers' reactions to promotions leads to improved targeting of clientele. The customer discovery tool provides a targeting system that can examine sparsely existing information regarding user behavior patterns during long time periods and analyze the feedback to promotions during marketing processes that comprise more than one promotion iteration.
The tool improves the quality of the network interaction analysis by including the analysis of user network interactions in a number of conscious or unconscious communication networks and combination of information which has been obtained from different sources. The tool also utilizes the information that can be extracted from different network interactions that each user consciously or unconsciously performs with applications and servers regarding the feedback the user has given to previous promotions. The tool also manages to utilize hyper sparse data from previous promotions to generate a new promotion.
That is to say, today actual purchases are often carried out electronically, and computer networks have actual information about genuine purchases made. Prior art current marketing systems are based on surveys, opinions, and extrapolations of the surveys. The tool for the first time allows one to obtain and use the actual information about genuine purchases because of the way the tool can look at data distributed over the network and is able to cope with the sheer volume of the information.
The customer discovery tool yields a list of potential customers targeted for promotion by combining data mining models, genetics algorithms, natural selection algorithms, pattern recognition algorithms, prediction algorithms and the like, based on any documented communication action or interaction a potential consumer may perform, inter alia: sending or receiving a Short Message Service (SMS), a Multimedia Messaging Service (MMS), an Enhanced Messaging Service (EMS), a phone call, or an IVR call. In addition, this may include switching between different
WEB pages or television channels, connecting to a specific wireless or wired network, using a satellite or cable receiver, reacting to an Interactive Voice Response (IVR), accessing e-mail and text-based WebPages using a mobile phone, and any other form of recordable interaction that a potential consumer can do consciously or unconsciously with any system or communication network or application server as recorded over the online world. That is to say the customer discovery tool teaches targeting of marketing activity based on empirical customer reaction data as opposed to known marketing methods, known marketing assumptions and traditional surveys. Such an approach may be referred to as empirical marketing, and is herein called customer discovery.
Using the customer discovery tool, the operator may empirically predict the likelihood that a specific interaction with a customer will result in a specific action. However the problem arises that since the customer discovery tool deals with empirical data related to numerous individual customers, the sheer quantity of data makes it hard for a user to interact therewith and make decisions based on a reasonable analysis.
The tool enables the discovery of potential customers. New and existing customers are identified as potential customers for offerings of products and services. Preferably, the tool identifies and targets potential customers identifies and allows a group of customers to be chosen for specific promotions in order to achieve the highest return on investment (ROI), by calculating a parameter such as the return time factor. However the act of choosing is difficult since the body of data is so large.
The tool may empirically examine the characteristics of customers who have responded to different promotions. But again, due to the quantity of data it is difficult to take the next step and generate a new targeted promotion based upon the common characteristics of those responding customers.
Using the preferred embodiment of the present invention, the potential consumers are offered promotions that match their specific needs and interests. The tool for identifying and targeting potential customers can address aspects in both the personal life and professional life of potential customers provided that the data management issues can be addressed. The tool has the ability to collect customer related information and to extract habits and fields-of-interest data about different potential customers therefrom. In addition, the tool has the ability to collect and analyze information about the reactions of potential consumers to products and services that the potential consumers have taken an interest in during previous promotions.
Information about the preferences of potential customers are extracted by the tool from various network interactions. The network interactions which can be monitored originate from various sources such as, for example, cellular service servers, ISP service servers, PSTN central server, etc. The gathered customer related information is used to generate an empirical decision regarding the suitability of the customer to a certain promotion. The physical meaning which is represented in the gathered customer related information is not analyzed. The tool does not differentiate between different customer related information by preferring one piece of information over the other. For example, customer related information regarding the age of the client is equally valued as customer related information regarding the customer SMS communication habits.
Unlike previous promotion tools, the physical meaning which is represented by the customer related information is not analyzed or valued during the promotion generation process. The customer discovery tool and like systems thus lack an intuitive way of presenting the large quantity of data acquired to allow rapid and correct decisions to be made.
SUMMARY OF THE INVENTION
According to one aspect of the present invention there is provided a method of providing an efficient promotion based on an analysis of a previous promotion, comprising: analysing data of the previous promotion to discover likely customers based on response to the previous promotion, transferring said analysis data onto a graph indicating cost of reaching a given number of customers against overall response rate, from said graph selecting a point, said point defining a certain cost and a certain response rate, and feeding said data back to a list of customers to target customers based on likely response rate from clusters giving a highest response rate downwards until said point is reached.
According to a second aspect of the present invention there is provided an interface device for allowing a user to interface with cumulative data in order to set parameters in respect thereof, comprising: a data input for accepting data being cumulative along a first axis; a calculation tool for calculation of values associated with said cumulative data for a second axis; a plotting tool for plotting said cumulative data against said first and second axes to form a graph; and a response input for receiving a user input defining a location on said graph, therefrom to define parameters for said cumulative data based on said location; said parameters being output by said interface device.
According to a third aspect of the present invention there is provided apparatus for obtaining parameters for a promotion based on data obtained from a previous promotion, comprising: a data analysis unit configured for analyzing data of the previous promotion to generate graph points; a data presentation unit configured for presenting said graph points as an interactive interface, said interactive interface being capable of receiving a user reaction; and a interface analysis unit configured for analyzing said user reaction in terms of graph points local to the user reaction and providing recommended parameters for a future promotion.
Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The materials, methods, and examples provided herein are illustrative only and not intended to be limiting.
Implementation of the method and system of the present invention involves performing or completing certain selected tasks or steps manually, automatically, or a combination thereof. Moreover, according to actual instrumentation and equipment of preferred embodiments of the method and system of the present invention, several selected steps could be implemented by hardware or by software on any operating system of any firmware or a combination thereof. For example, as hardware, selected steps of the invention could be implemented as a chip or a circuit. As software, selected steps of the invention could be implemented as a plurality of software instructions being executed by a computer using any suitable operating system. In any case, selected steps of the method and system of the invention could be described as being performed by a data processor, such as a computing platform for executing a plurality of instructions.
BRIEF DESCRIPTION OF THE DRAWINGS
The invention is herein described, by way of example only, with reference to the accompanying drawings. With specific reference now to the drawings in detail, it is stressed that the particulars shown are by way of example and for purposes of illustrative discussion of the preferred embodiments of the present invention only, and are presented in order to provide what is believed to be the most useful and readily understood description of the principles and conceptual aspects of the invention. In this regard, no attempt is made to show structural details of the invention in more detail than is necessary for a fundamental understanding of the invention, the description taken with the drawings making apparent to those skilled in the art how the several forms of the invention may be embodied in practice.
In the drawings:
Fig. 1 is a simplified block diagram illustrating a first preferred embodiment of the present invention for selecting parameters for a promotion based on interpretation of data from a previous promotion. Fig. 2 is a simplified block diagrams showing data flow through a system for selecting parameters for a promotion based on interpretation of data from a previous promotion, according to a preferred embodiment of the present invention.
Fig. 3 is a simplified flow chart showing operation of a method selecting parameters for a promotion based on interpretation of data from a previous promotion, according to a preferred embodiment of the present invention.
Fig. 4 is a simplified diagram showing an interface according to a first preferred embodiment of the present invention based on a three-axis graph. Fig. 5 is a simplified block diagram illustrating units of a system according to the preferred embodiments of the present invention.
Figs. 6 - 10 are simplified schematic diagrams showing how multiple promotions can be efficiently targeted at the same group of customers according to preferred embodiments of the present invention.
DESCRIPTION OF THE PREFERRED EMBODIMENTS The present embodiments comprise a system and method that integrates relevant information, for example data obtained through the customer discover tool referred to in the background into a single user interface that allows a business user to make an informed decision. The user is provided with an interface that allows parameters to be set for future activity based on the obtained data from the previous activity. The previous activity may be a promotion and the data obtained may be customer discovery data. The interface may use data of identified customers to show how a new campaign can be effectively targeted and show trade-offs in resources used against projected response rate. A decision may then be made concerning the parameters to be used in a future promotion. The power of the interface to help in decision making may help a business user to optimize the resources of his organization, thus to maximize the profits and to avoid a potential loss to his organization.
By combining and transforming all relevant parameters, to make an economic decision, in one all-inclusive user interface, the service response model provides a tool for a user to make the appropriate economic decision under the constraints of his organization. More generally, the system provides an interface for making decisions based on cumulative data. The cumulative data is presented as a graph so that rates of change are apparent and the user can then choose a decision point from the graph. The decision point is translated into parameters which are then used in making selections based on the original data. The principles and operation of an apparatus and method according to the present invention may be better understood with reference to the drawings and accompanying description. Before explaining at least one embodiment of the invention in detail, it is to be understood that the invention is not limited in its application to the details of construction and the arrangement of the components set forth in the following description or illustrated in the drawings. The invention is capable of other embodiments or of being practiced or carried out in various ways. Also, it is to be understood that the phraseology and terminology employed herein is for the purpose of description and should not be regarded as limiting. The following terms are used:
- User or User identifier: is either a mobile user obtained by his unique MSISDN or any other unique identifier for a specific user. Such mobile users may be potential customers for a promotion targeted over the mobile network.
- Promotion: Any promotion including content promotion, advertising, registration invitation, churn management promotion, price plan promotion or any other form of message that may be delivered to a potential customer by any method (e.g. SMS, MMS, email, Print, mail, internet advertisement etc.)
Recall rate: the percentage of potential customers the promotion is to attain. 100% recall means 100% of potential market size.
Promotion size: the number of potential customers that are to be targeted with the promotion - Response rate: the number of potential customers that respond to the promotion relative to the promotion size.
Target point: represents a feasible combination of response rate, recall rate and promotion size.
Information provider: A unit that provides all feasible target points for a specific promotion.
Operator: an operator, including an organization, wishing to run a promotion, also referred to as a promoter.
ROI: Return on investment.
Reference is now made to Fig. 1, which shows apparatus for obtaining parameters for a promotion based on data obtained from a previous promotion. The apparatus 10 makes use of a customer discovery tool 12 which obtains data from an existing promotion. The customer discovery tool preferably includes customer data and customer profiles. The tool provides details of those customers who actually responded to the earlier promotion. The customers who responded can be mapped on a plane, based on their profile information, and data mining models, natural selection and genetic algorithms may then be used to find where the responding customers cluster on the map and which other customers fit the profiles of the clusters and can therefore also be identified as potential customers. The actual customers together with potential customers that cluster with the actual customers may then be used to form new promotion lists.
The customer discovery tool includes a discovery unit 14 for empirically analyzing customer data regarding customer reaction to the earlier promotion. The analysis identifies groupings or clusters of customers differentiated by the reactions, meaning those who responded in some way to the promotion. Then a targeting unit, 16 targets customers belonging to the groups discovered from customers showing correlated reactions during the analysis stage.
The discovery tool thus yields a list of potential customers targeted for promotion by combining data mining models, genetics algorithms, natural selection algorithms, pattern recognition algorithms, prediction algorithms and the like, based on any documented communication action or interaction a potential consumer may perform, inter alia: sending or receiving a Short Message Service (SMS), a Multimedia Messaging Service (MMS), an Enhanced Messaging Service (EMS), a phone call, or an IVR call. In addition, this may include switching between different WEB pages or television channels, connecting to a specific wireless or wired network, using a satellite or cable receiver, reacting to an Interactive Voice Response (IVR), accessing e-mail and text-based WebPages using a mobile phone, and any other form of recordable interaction that a potential consumer can do consciously or unconsciously with any system or communication network or application server as recorded over the online world.
Thus the customer discovery tool 12 carries out targeting of marketing activity based on actual customer data, as opposed to traditional marketing methods, known marketing assumptions and traditional surveys. Such an approach may be referred to as empirical marketing, and is herein called customer discovery.
The customer discovery tool may discern certain customers who responded very easily to a basic promotion, and others who took longer, or who required more promotion until they responded. That is to say, the customer discovery tool in fact finds out more about the potential customer than merely binary information about his likelihood to respond.
The customer discovery data is provided through API 18 to customer - point analyzer 20. In general it is possible to analyze the data, and the customers within the data, to define a cost or difficulty in obtaining a response from a given customer, so that the customers can be ordered in terms of ease in getting a response. Certain customers are presumably easy to reach and influence, and others are presumably difficult to reach and influence. The customer - point analyzer uses the above presumptions to order the customer data into data points, each of which is a cumulative number of customers achieved for a certain amount of promotional effort.
The points are passed to interface unit 22 which draws them as a graph, as per Fig. 4, which will be described in greater detail below. The graph shows the number of customers that can be reached by a promotion against the effort put into reaching them. As will be explained below, the axes of the graph can be labeled with quantifiers thus to give a cost of reaching a given number of customers etc.
The user can then provide input to the graph to provide parameters to define a particular promotion. For example he can press on a particular point on the graph to define a given level of effort in an upcoming promotion based on the predicted success rate.
The result of the user interaction is to provide one or more parameters, which can now be used to define a promotion. The parameters are now fed back to the customer discover tool 12 so that the new parameters can be superimposed on the customers in the tool. Using the parameters a list of suitable customers can be created and then targeted by the promotion using the targeting unit 16.
Reference is now made to Fig. 2, which is a simplified diagram illustrating a flow of data according to a preferred embodiment of the present invention. Ovals represent data and rectangles represent processing entities.
Data 30 of the customers is available from the customer discovery tool 12. A data analysis unit, 32, in effect the customer to point analyzer, creates data points 34, typically cumulative. The data points 34 are arranged into a graph 36 by data presentation unit or interface 38. An interface analysis unit 40 then reads a user interaction 37 with the graph 36 in terms of graph points local to the user reaction, and produces one or more parameters 42 which are then fed back to the individual customers in the customer discovery tool, as recommendations for a future promotion.
Graph 36 is preferably provided as a three-axis graph, as will be described in greater detail below. Preferably, one axis is an independent axis and the remaining axes are interdependent on each other, for example having a crossed values relationship. In the case of Fig. 4, discussed below, the top and the bottom axis have a crossed values relationship. That is to say the bottom axis goes from left to right while the upper axis goes from right to left. The values on each axis are not independent of the other. The top value may define or affect the bottom value and vice versa.
In one embodiment the data presentation unit or interface 38 inserts a point beyond which the cost of reaching an additional customer exceeds the intrinsic value of a customer in the promotion. That is to say the graph indicates the economic limitations that apply to the promotion. Other forms of unfeasibility may also be marked on the graph. For example a promotion may be limited by infrastructure availability. Certain levels of promotion may be prohibited by the limitations of the available bandwidth.
The data points 34 may comprise data such as a response rate at that point on the graph, a number of promotional contacts, and a cumulative or absolute number of responses to that point, or any other information that is believed to be useful.
For any point on the graph is to possible to calculate a minimum promotion size, a cost of promotion, a response value and a potential market size. The minimum promotion size and cost of promotion may specifically be dependent on selection by the customer interaction.
Reference is now made to Fig. 3, which is a simplified flow diagram illustrating a method of providing an efficient promotion based on an analysis of a previous promotion. The method comprises stages of:
50 obtaining data of the previous promotion to formulate likely customer responses based on response to the previous promotion,
52 transferring the analysis onto a graph indicating cost of reaching a given number of customers against overall response rate,
54 allowing the user to select a point, thereby defining a certain cost and a certain response rate desired for the new promotion, and 56 feeding parameters based on the selected point back to the list of customers, so that the system targets customers based on their likely response rate from those with a highest response rate downwards until the point selected by the user is reached.
Reference is now made to Fig. 4, which is a simplified diagram illustrating the graph 36 at the center of the user interface 38 of the presently preferred embodiments.
The user interface 38 of the present embodiments may provide a graph with three axes, each axis being a domain affecting the decision to be made on the promotion. For example the three axes may be:
1. Response rate,
2. Recall rate
3. Promotion size.
Additionally, the interface summarizes the information available regarding the promotion in such a way loss of information is minimized or avoided. Moreover, the graph may clearly mark, visually, any non-economical target points, as explained.
The system receives all relevant information for a given promotion and presents it in such a way that a user can make a decision and input that decision with the click of a mouse. With a single click a new promotion can be defined and launched.
Upon opening the user interface, the system loads the target points and any economic restrictions, such as minimum required response rate. The information is supplied by the operator and displayed in the information provider. The information may be obtained by the user in any way desired. The system analyzes feasible target points extracted from the existing data and creates a new set of target points. The new set contains the same information as the original set, but consists of only enough target points for a readable presentation of the information - The manageable information set.
The system plots the manageable information set on a three axes graph. The bottom axis shows the promotion target group size. The left axis shows the total expected users. The top axis shows the response rate. Each point on the graph is a possible (but not necessarily realistic) target point.
The system marks in one way, say using a red circle, all the feasible target points with response rate lower then the required minimum response rate as provided by the business user. These points reflect promotions that are feasible in the sense that the could be carried out, but which may not produce an economic return, that is to say the organization might experience economic loss.
The system marks in another way, say in yellow, all target points that are not attainable because of technical system constraints. For example, the system might not be able to deliver such a large number of video messages on time due to lack of system capacity, for example lack of available network bandwidth etc, or a promotion involving personalized messages to customers may be limited by organizational bandwidth in preparing the personalized messages. The business user selects the desired target point by clicking a point on the graph. The system knows the cost of each promotional message, and the profit from a positive response. The system also knows the response rate over any given group of customers, so that a given point can be categorized as economical or non-economical. If the business user selects a non-economical target point; the system preferably issues a warning.
A summary of economic and statistical implications of the selected target point are presented to the business user for confirmation. The summary preferably includes the following:
I. The mean cost to reach a customer. II. The cost to obtain an additional customer.
III. The return on investment in periods (days, months, years) for all customers and for an additional customer.
IV. ROI for all customers and for an additional customer.
On confirmation, the system provides a notification regarding the creation of a target group of customers with a certain expected response rate, recall rate and promotion group size. The target group then receives the promotion.
An analysis of the graph in Fig. 4 shows three regions, a steep initial region, where a small increase in promotion size leads to a large increase in customers, an intermediate region with a falling curve where the effectiveness of the promotion gradually reduces and a relatively flat final region where large additional increases in effort bring in very few additional customers. A promoter would normally be expected to include the initial region in his promotion and exclude the final region, using his judgment as to where in the intermediate region to end the promotion. The system operation includes the following steps:
One. Large quantities of information and parameters are collected from a previous promotion. The information collection may involve an information provider and the user of the promotions. The data may be collected using the customer discovery tool 12 as explained above, but other sources may be used as well or instead.
Two: The system converts the information set including target points to a manageable set for presentation purposes, as explained above. For example data points based on each individual customer may be merged into combined data points representing a hundred customers.
Three: The system presents the feasible target point on a three axis graph, such as that of Fig. 4.
Four: Indications and warnings are provided for possible non-economical decisions - for example target points in which the total expected costs exceed the total expected revenue from a promotion, as explained.
Five: The system marks target points that are not attainable because of technical system constrains - available bandwidth, time to market etc, as explained.
Six: The user clicks on a target point on the graph. The point defines the parameters of the promotion according to the three axes, so that the user effectively selects a target group for a specific promotion. The parameters ensure that the promotion is aimed to meet the promoter's organization goals. If the user selects a non-economic point, a warning may be issued.
Seven: The system presents a summary of economic and statistical implications of the selected target point. Eight: The system notifies a back-end system on the creation of a target group with the specified response rate, promotion size and potential positive responses. The customers to be included in the target group are preferably available from the customer discovery tool.
Reference is now made to Fig. 5, which illustrates the interfacing system as a series of modules, an information receiver module 60, a transformation module 62 and a notification module 64. Parts of the overall system not regarded as belonging to the Interfacing system are referred to as the back-end system and include the customer discovery tool. The information receiver module 60 is an interface between the back-end system and the service response model, and is designed to obtain all possible points which could easily be numbered in the tens or hundreds, and also obtain or calculate the data values which go with each one of them, as well as all the promotion specific metrics such as minimum response rate for ROI, cost of 1 promotion, value of response. The module runs sanity checks on the data, and then the data, including the target points and business restrictions into the transformation model.
The transformation module 62 transforms the information received from the information receiver module as target points, to a manageable sized set of target points. Also, the transformation module flags the target points which have a response rate above the minimum required response rate. The transformation module selects some of the reduced number of points, say around ten, based on business logic to mark as providing maximum profit, or maximum profit in a given region, and marks bad or non-profitable and otherwise unattainable points as discussed above. The end result is displayed to form the interactive user interface.
The transformation module thus produces the data that is used directly in the graph of Fig. 4.
The notification module 64 produces messages. As the promoter clicks on a target point on the service response model graph, the notification module notifies the back-end system regarding the request so that creation of a target group can be carried out with the selected parameters from the three axes: promotion size, response rate and recall rate corresponding to the target point. That is to say, once the operator selects a point on the graph, the notification module translates the selected point, say point no. 6, into the real values behind it, that is a number of promotions to send, response rate etc, and these values are then transmitted as parameters back into the customer discovery system for the generation of the customer list for the promotion.
Referring again to Fig. 4 and the graph used in the interface may be varied. For example the the upper axis, currently the response rate axis, can hold different parameters such as: • Money - how much money any given point on the graph produces.
• ROI - When (in terms of time) the investment, or the cost of the promotion may be expected to be covered by the revenues from the users who accept the promotion offering. • Cost of promotion - what is the cost of promoting the offering to the group represented by the selected point on the graph.
• Cost of next customer - what is the cost of acquiring the next customer (below the selected point) • Cost of last customer - what is the cost of acquiring the last (and most expensive) customer in the promotion group represented by the point on the graph.
Reference is now made to Fig. 6 which is a simplified diagram illustrating in schematic form a series of three promotions as they might be targeted at the same group of customers. In Fig. 6, graph 70 shows three different possible promotions for ringtones, which it is intended to market to the same overall group of potential customers based on response rates to previous promotions. Each promotion is for ringtones and is aimed at users who have shown interest in ringtones, but not all customers seem to be responsive to the same marketing techniques, and the question is one of launching the three promotions independently or somehow merging them.
Each promotion has a value marked thereon, which is the number of potential users multiplied by the response rate.
If the promotions are to be merged then how should they be merged? In any event many consumers would probably react negatively if targeted by all three promotions.
Reference is now made to Fig. 7, in which the freering and four ring promotions are selected for merging. In this case the freering promotion has a value of $8k and the four ring promotion has a value of $ 13k.
Fig. 8 shows the three promotions 72, 74 and 76 following the merger between promotions 74 and 76. The total value is now 16k which is not the sum of the two original promotions. Neither is the total number of potential customers the sum of the individual promotions. The reason for the discrepancy is that many of the potential customers for the two promotions are the same. For each common customer it is then determined which of the two promotions gives a higher value. For example if in the freering promotion the customer has a 30% chance of paying $5, giving a total value of $1.50, and in the four ring promotion the same customer has a 73 chance of paying $3, giving a total of $2.19, then it is more efficient to target this user with the four ring promotion than with the freering promotion. Thus such a customer would be targeted with the four ring promotion.
Fig. 9 shows the selection of the two ring promotion for marking with the merged four ring and freering promotions. Fig. 10 shows the result of the merging. The interface of Fig. 4 can be used to define the size of a given promotion before merging is carried out. However preferably the interface is used to select the final resources put into the merged promotion.
It is expected that during the life of this patent many relevant devices and systems will be developed and the scope of the terms herein, is intended to include all such new technologies a priori.
It is appreciated that certain features of the invention, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable subcombination.
Although the invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, it is intended to embrace all such alternatives, modifications and variations that fall within the spirit and broad scope of the appended claims. All publications, patents, and patent applications mentioned in this specification are herein incorporated in their entirety by reference into the specification, to the same extent as if each individual publication, patent or patent application was specifically and individually indicated to be incorporated herein by reference, hi addition, citation or identification of any reference in this application shall not be construed as an admission that such reference is available as prior art to the present invention.

Claims

CLAIMSWhat is claimed is:
1. Apparatus for obtaining parameters for a promotion based on data obtained from a previous promotion, comprising: a data analysis unit configured for analyzing data of the previous promotion to generate graph points; a data presentation unit configured for presenting said graph points as an interactive interface, said interactive interface being capable of receiving a user reaction; and a interface analysis unit configured for analyzing said user reaction in terms of graph points local to the user reaction and providing recommended parameters for a future promotion.
2. The apparatus of claim 1, wherein said data presentation unit is configured to present said graph points as a three-axis graph.
3. The apparatus of claim 2, wherein said data presentation unit is configured such that a first of said three axes is an independent axis and the remaining axes are interdependent.
4. The apparatus of claim 3, wherein said data presentation unit is configured such that said remaining axes are interdependent in that they have a crossed values relationship.
5. The apparatus of claim 1, wherein the data of a previous promotion comprises customer data wherein customers responding to said previous promotion are clustered.
6. The apparatus of claim 5, wherein said data analysis unit is configured to analyze said data by ordering customers according to likelihood of response or value of response indicated by said previous promotion data.
7. The apparatus of claim 1, wherein data presentation unit is configured to insert a point beyond which the cost of reaching an additional customer exceeds a value of reaching said additional customer.
8. The apparatus of claim 1, wherein said data presentation unit is configured to mark regions of unfeasibility.
9. The apparatus of claim 1, further comprising a parameter feedback unit for feeding back data from the interface analysis unit back to the analyzed data of the previous promotion to obtain a list of customers to target in the present promotion.
10. The apparatus of claim 1, wherein said graph points each comprise a response rate, a number of promotional contacts, and a cumulative number of responses.
11. The apparatus of claim 10, wherein for each proposed new promotion there is provided a minimum promotion size, a cost of promotion, a response value and a potential market size, and wherein the minimum promotion size and cost of promotion are dependent on selection by said customer interaction.
12. The apparatus of claim 1, wherein said data analysis unit is configured to arrange customer data in respect of a plurality of promotions and to emerge said promotions by assigning a given customer to the one of said plurality of promotions for which said given customer shows a highest potential return.
13. A method of providing an efficient promotion based on an analysis of a previous promotion, comprising: analysing data of the previous promotion to discover likely customers based on response to the previous promotion, transferring said analysis data onto a graph indicating cost of reaching a given number of customers against overall response rate, from said graph selecting a point, said point defining a certain cost and a certain response rate, and feeding said data back to a list of customers to target customers based on likely response rale from clusters giving a highest response rate downwards until said point is reached.
14. An interface device for allowing a user to interface with cumulative data in order to set parameters in respect thereof, comprising: a data input for accepting data being cumulative along a first axis; a calculation tool for calculation of values associated with said cumulative data for a second axis; a plotting tool for plotting said cumulative data against said first and second axes to form a graph; and a response input for receiving a user input defining a location on said graph, therefrom to define parameters for said cumulative data based on said location; said parameters being output by said interface device.
15. The interface device of claim 14, wherein the calculation tool is further configured to calculate values for a third axis, said third axis comprising values functionally correlated with those of the second axis.
PCT/IL2007/000234 2006-02-21 2007-02-21 Return rate optimization system and method for promotions WO2007096876A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US77467206P 2006-02-21 2006-02-21
US60/774,672 2006-02-21

Publications (2)

Publication Number Publication Date
WO2007096876A2 true WO2007096876A2 (en) 2007-08-30
WO2007096876A3 WO2007096876A3 (en) 2009-04-09

Family

ID=38437768

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IL2007/000234 WO2007096876A2 (en) 2006-02-21 2007-02-21 Return rate optimization system and method for promotions

Country Status (1)

Country Link
WO (1) WO2007096876A2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7563835B2 (en) 2001-12-28 2009-07-21 Sun Chemical Corporation Solventless universal colorants

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5704017A (en) * 1996-02-16 1997-12-30 Microsoft Corporation Collaborative filtering utilizing a belief network
US6236975B1 (en) * 1998-09-29 2001-05-22 Ignite Sales, Inc. System and method for profiling customers for targeted marketing
US6327574B1 (en) * 1998-07-07 2001-12-04 Encirq Corporation Hierarchical models of consumer attributes for targeting content in a privacy-preserving manner
US6430539B1 (en) * 1999-05-06 2002-08-06 Hnc Software Predictive modeling of consumer financial behavior
US6567786B1 (en) * 1999-09-16 2003-05-20 International Business Machines Corporation System and method for increasing the effectiveness of customer contact strategies
US7287000B2 (en) * 2000-11-15 2007-10-23 Jda Software Group, Inc. Configurable pricing optimization system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5704017A (en) * 1996-02-16 1997-12-30 Microsoft Corporation Collaborative filtering utilizing a belief network
US6327574B1 (en) * 1998-07-07 2001-12-04 Encirq Corporation Hierarchical models of consumer attributes for targeting content in a privacy-preserving manner
US6236975B1 (en) * 1998-09-29 2001-05-22 Ignite Sales, Inc. System and method for profiling customers for targeted marketing
US6430539B1 (en) * 1999-05-06 2002-08-06 Hnc Software Predictive modeling of consumer financial behavior
US6567786B1 (en) * 1999-09-16 2003-05-20 International Business Machines Corporation System and method for increasing the effectiveness of customer contact strategies
US7287000B2 (en) * 2000-11-15 2007-10-23 Jda Software Group, Inc. Configurable pricing optimization system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7563835B2 (en) 2001-12-28 2009-07-21 Sun Chemical Corporation Solventless universal colorants

Also Published As

Publication number Publication date
WO2007096876A3 (en) 2009-04-09

Similar Documents

Publication Publication Date Title
US20090070129A1 (en) Customer Discovery and Identification System and Method
US9477930B2 (en) Cross channel optimization systems and methods
US20170243257A1 (en) Methods and apparatuses for sorting lists for presentation
US9245021B2 (en) Method and system for tracking online promotional source to offline activity
US20080201188A1 (en) Niche-oriented advertising networks platform and methods of operating same
US20080255929A1 (en) Method for Obtaining Customer Feedback Through Text Messaging
US20030014304A1 (en) Method of analyzing internet advertising effects
US20040030597A1 (en) Method and system of optimizing the response and profitability of a marketing program
US20110022475A1 (en) Distribution of promotional data and receipt of customers' reactions to the data
US20130204700A1 (en) System, method and computer program product for prediction based on user interactions history
EP2246813A1 (en) Method and system for improving personalization of advertising for mobile devices using peer rating
AU2009302252A1 (en) Managing internet advertising and promotional content
WO2014012175A2 (en) Measuring influence in a social network
KR20110100030A (en) Marketing effectiveness measurement system, method thereof and recorded medium recorded with program thereof
US9811843B2 (en) System and method for targeting user interests based on mobile call logs
CA2824890A1 (en) Device for measuring spasticity
US20030144898A1 (en) System, method and computer program product for effective content management in a pull environment
JP7344234B2 (en) Method and system for automatic call routing without caller intervention using anonymous online user behavior
US8712844B2 (en) Use of natural query events to improve online advertising campaigns
WO2007096876A2 (en) Return rate optimization system and method for promotions
KR20070016229A (en) The reaction exponent retrieval according to an every kind promotion reaction information and application
WO2001037119A2 (en) Apparatus and method for providing advertising on internet-enabled channels
JP6230209B2 (en) Promotion system for outbound marketing and promotion method for outbound marketing
KR102607653B1 (en) A Telemarketing performance evaluation and improvement method by mobile advertising media
US20230351423A1 (en) Dynamic selection of groups of users in a computerized system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application
NENP Non-entry into the national phase in:

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 07706170

Country of ref document: EP

Kind code of ref document: A2