# US 2021/0279747 A1 · Systems and methods for tracking consumer electronic spend behavior to predict attrition > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0279747 A1 - Document ID: US20210279747A1 - Status: Published application - Kind: A1 - Application number: 17/330,467 - Filed: 2021-05-26 - Published: 2021-09-09 - Earliest claimed: 2016-12-16 - Assignees: Worldpay, LLC - Applicants: Worldpay, LLC - Inventors: Brent BADGER; Dennis KETTLER - Web page: https://patentgrep.com/patent/US20210279747A1 ## CPC - G06Q 30/0202: Market predictions or forecasting for commercial activities - G06Q 30/0241: Advertisements - 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 ## Abstract Systems and methods are disclosed for tracking consumer spend behavior to predict attrition. One method includes: receiving past transaction data related to a plurality of past payment transactions of a consumer; receiving environmental and/or behavioral data associated with each of the past payment transactions of the consumer; determining a spend behavior model of the consumer; subsequent to determining the spend behavior model of the consumer, receiving transaction data related to one or more current payment transactions of the consumer; receiving environmental and/or behavioral data associated with the one or more current payment transactions; determining, based on an analysis of the current transaction data and environmental and/or behavioral data associated with each of the current payment transactions, a current spend behavior of the consumer; and determining, based on a comparison of the current spend behavior with the spend behavior model, the likelihood of an attrition of the current spend behavior. ## Claims ### Claim at position 1 1-20. (canceled) ### Claim 21 A computer-implemented method of tracking consumer spend behavior to predict attrition, comprising: receiving, in a database associated with a profiler computing system, environmental and/or behavioral data associated with transaction data of a consumer; generating, by a processor of the profiler computing system, a spend behavior model of the consumer based on the transaction data of the consumer; receiving, in the database associated with the profiler computing system by way of a networked user device, transaction data of one or more current payment transactions of the consumer; generating, by an electronic transaction processor, payment tokens based on the transaction data of one or more current payment transactions of the consumer; determining, by the processor of the profiler computing system, based on the spend behavior model, a current spend behavior of the consumer; identifying, by the processor of the profiler computing system, based on the spend behavior model and the payment tokens, one or more anomalous transactions among the one or more current payment transactions; and determining, by the processor of the profiler computing system, based on the identified one or more anomalous transactions, a likelihood of an attrition of the current spend behavior. ### Claim 22 (depends on 21) The method of claim 21, wherein determining the likelihood of an attrition of the current spend behavior further comprises: determining an inconsistency in a spend behavior of the consumer by comparing the current spend behavior with the spend behavior model; and determining the likelihood of an attrition of the current spend behavior based on the determined inconsistency. ### Claim 23 (depends on 22) The method of claim 22, wherein the determined inconsistency in a spend behavior includes one or more of: a missed payment transaction that is otherwise predicted to occur based on the spend behavior model; a change in a relative proportion of one or more payment networks used by the consumer in payment transactions; a change in an environmental and/or behavioral data; or a change in a purchasing behavior related to a good, service and/or stock keeping unit. ### Claim 24 (depends on 21) The method of claim 21, further comprising: updating the spend behavior model based on the determined likelihood of the attrition of the current spend behavior. ### Claim 25 (depends on 21) The method of claim 21, further comprising: predicting a customer lifetime value for a merchant based on one or more of the spend behavior model, the current spend behavior, or the likelihood of the attrition of the current spend behavior. ### Claim 26 (depends on 21) The method of claim 21, wherein transaction data is data electronically received from one or more merchants to effectuate an electronic transfer of funds via an electronic payment network. ### Claim 27 (depends on 21) The method of claim 21, wherein one or more of the transaction data or environmental and/or behavioral data is further received from one or more of: a stock keeping unit of a merchant; or an authorized third party. ### Claim 28 (depends on 21) The method of claim 21, wherein the environmental and/or behavioral data associated with a payment transaction includes, one or more of: data related to a channel of purchase used in the payment transaction; temporal data related to the payment transaction; data related to a geographical location of the consumer or merchant in the payment transaction; data related to the merchant in the payment transaction; data related to a good or service being transacted for in the payment transaction; data related to any online activity of the consumer; and transaction data related to the payment transaction. ### Claim 29 (depends on 21) The method of claim 21, wherein a spend behavior of the consumer includes one or more of: habitually purchasing from a merchant and/or group of merchants; habitually purchasing using one or more channels of purchase; habitually purchasing a good and/or service, or a category of good and/or service; habitually using of one or more payment methods and/or payment vehicles; and trends in the spend behavior of the consumer. ### Claim 30 A system of tracking consumer spend behavior to predict attrition, comprising a data storage device storing instructions for tracking consumer spend behavior to predict attrition; and a processor configured to execute the instructions to perform a method including: receiving, in a database associated with a profiler computing system, environmental and/or behavioral data associated with transaction data of a consumer; generating, by a processor of the profiler computing system, a spend behavior model of the consumer based on the transaction data of the consumer; receiving, in the database associated with the profiler computing system by way of a networked user device, transaction data of one or more current payment transactions of the consumer; generating, by an electronic transaction processor, payment tokens based on the transaction data of one or more current payment transactions of the consumer; determining, by the processor of the profiler computing system, based on the spend behavior model, a current spend behavior of the consumer; identifying, by the processor of the profiler computing system, based on the spend behavior model and the payment tokens, one or more anomalous transactions among the one or more current payment transactions; and determining, by the processor of the profiler computing system, based on the identified one or more anomalous transactions, a likelihood of an attrition of the current spend behavior. ### Claim 31 (depends on 30) The system of claim 30, wherein determining the likelihood of an attrition of the current spend behavior further comprises: determining an inconsistency in a spend behavior of the consumer, by comparing the current spend behavior with the spend behavior model; and determining the likelihood of an attrition of the current spend behavior based on the determined inconsistency. ### Claim 32 (depends on 31) The system of claim 31, wherein the determined inconsistency in a spend behavior includes one or more of: a missed payment transaction that is otherwise predicted to occur based on the spend behavior model; a change in a relative proportion of one or more payment networks used by the consumer in payment transactions; a change in an environmental and/or behavioral data; or a change in a purchasing behavior related to a good, service and/or stock keeping unit. ### Claim 33 (depends on 31) The system of claim 31, further comprising: updating the spend behavior model based on the determined likelihood of the attrition of the current spend behavior. ### Claim 34 (depends on 30) The system of claim 30, further comprising: predicting a customer lifetime value for a merchant based on one or more of the spend behavior model, the current spend behavior, or the likelihood of the attrition of the current spend behavior. ### Claim 35 (depends on 30) The system of claim 30, wherein transaction data is data electronically received from one or more merchants to effectuate an electronic transfer of funds via an electronic payment network. ### Claim 36 (depends on 30) The system of claim 30, wherein one or more of the transaction data or environmental and/or behavioral data is further received from one or more of: a stock keeping unit of a merchant; or an authorized third party. ### Claim 37 (depends on 30) The system of claim 30, wherein the environmental and/or behavioral data associated with a payment transaction includes, one or more of: data related to a channel of purchase used in the payment transaction; temporal data related to the payment transaction; data related to a geographical location of the consumer or merchant in the payment transaction; data related to the merchant in the payment transaction; data related to a good or service being transacted for in the payment transaction; data related to any online activity of the consumer; and transaction data related to the payment transaction. ### Claim 38 (depends on 30) The system of claim 30, wherein a spend behavior of the consumer includes one or more of: habitually purchasing from a merchant and/or group of merchants; habitually purchasing using one or more channels of purchase; habitually purchasing a good and/or service, or a category of good and/or service; habitually using of one or more payment methods and/or payment vehicles; and trends in the spend behavior of the consumer. ### Claim 39 A non-transitory machine-readable medium stores instructions that, when executed by profiler computing system, causes the profiler computing system to perform a method for tracking consumer spend behavior to predict attrition, the method comprising: receiving, in a database associated with a profiler computing system, environmental and/or behavioral data associated with transaction data of a consumer; generating, by a processor of the profiler computing system, a spend behavior model of the consumer based on the transaction data of the consumer; receiving, in the database associated with the profiler computing system by way of a networked user device, transaction data of one or more current payment transactions of the consumer; generating, by an electronic transaction processor, payment tokens based on the transaction data of one or more current payment transactions of the consumer; determining, by the processor of the profiler computing system, based on the spend behavior model, a current spend behavior of the consumer; identifying, by the processor of the profiler computing system, based on the spend behavior model and the payment tokens, one or more anomalous transactions among the one or more current payment transactions; and determining, by the processor of the profiler computing system, based on the identified one or more anomalous transactions, a likelihood of an attrition of the current spend behavior. ### Claim 40 (depends on 39) The non-transitory machine-readable medium of claim 39, wherein determining the likelihood of an attrition of the current spend behavior further comprises: determining an inconsistency in a spend behavior of the consumer, by comparing the current spend behavior with the spend behavior model; and determining the likelihood of an attrition of the current spend behavior based on the determined inconsistency.