Computer-Implemented Data Storage Systems and Methods for Use with Predictive Model Systems

Abstract

Systems and methods for performing fraud detection. As an example, a system and method can be configured to contain a raw data repository for storing raw data related to financial transactions. A data store contains rules to indicate how many generations or to indicate a time period within which data items are to be stored in the raw data repository. Data items stored in the raw data repository are then accessed by a predictive model in order to perform fraud detection.

1 . A computer-implemented method comprising:
 presenting, on a graphical user interface, an entity type selector configured to receive a selection of one of multiple different entities for a type of financial analysis;   receiving, from the entity type selector, a selection of an a first entity;   accessing, from at least one of a plurality of raw data repositories, stored raw data associated with the selected first entity, wherein the stored raw data includes financial transaction data records, wherein the raw data repositories are configured for the storage of raw data associated with multiple different entities;   presenting, on the graphical user interface, an analysis type selector configured to receive a selection of one of multiple different types of financial analyses, wherein the multiple different types of financial analyses includes:
 a fraud analysis type configured to analyze the stored raw data to perform fraud detection for a selected entity, and 
 a non-fraud analysis type configured to analyze the stored raw data to generate information that is not related to fraud detection for a selected entity; 
   receiving, from the analysis type selector, a section for the non-fraud analysis type of financial analysis; and   performing, on a processing unit, the non-fraud analysis type of financial analysis to generate information that is not related to fraud detection for the first entity.   
     
     
         2 . The method of  claim 1 , wherein the non-fraud analysis type of analysis further facilitates predicting an attrition score with respect to the first entity, and wherein the information includes an attrition score for the first entity. 
     
     
         3 . The method of  claim 2 , wherein the first entity is a merchant engaged in a customer relationship with a financial service provider, and wherein the attrition score indicates a likelihood the customer relationship will cease. 
     
     
         4 . The method of  claim 3 , wherein the financial service provider applies a fee structure to the first entity, and wherein the accessed raw data includes information that represents the fee structure, and wherein the attrition score is based on the information that represents the fee structure. 
     
     
         5 . The method of  claim 3 , wherein the accessed raw data includes a data record that indicates a history of payments made by the first entity to the financial service provider, and wherein the attrition score is based on the accessed data record. 
     
     
         6 . The method of  claim 5 , wherein the data record further indicates timeliness of the payments. 
     
     
         7 . The method of  claim 6 , further comprising:
 receiving a selection of a second entity, wherein the selection of the second entity is inputted using the entity type selector, and wherein the second entity is an individual account holder who maintains an account serviced by the financial service provider;   receiving a selection of the fraud detection analysis type of analysis, wherein the selection of the fraud detection analysis type of analysis is inputted using the analysis type selector;   accessing raw data associated with transactional activity involving the account; and   detecting fraud involving the account, wherein detecting fraud includes analyzing the raw data associated with the transactional activity by applying the fraud detection analysis type of analysis.   
     
     
         8 . The method of  claim 7 , wherein the raw data associated with the transactional activity is accessed from another of the plurality of raw data depositories, and wherein the plurality of raw data depositories are maintained in a distributed environment. 
     
     
         9 . The method of  claim 1 , further comprising:
 receiving a selection of the fraud detection analysis type of financial analysis, wherein the selection of the fraud detection analysis type is inputted using the analysis type selector;   in response to receiving the selection of the fraud detection analysis type, accessing additional raw data associated with the first entity, wherein the additional raw data includes data representing transactional activities involving multiple types of credit cards; and   detecting fraud involving the first entity, wherein detecting fraud includes analyzing the additional raw data using the fraud detection analysis type of financial analysis, and wherein detecting fraud includes calculating an incidence of fraud amongst transactions involving the first entity.   
     
     
         10 . A computer computer-program product comprising a non-transitory machine-readable store medium having instructions stored therein, wherein the instructions are executable to cause a computing apparatus to perform operations including:
 presenting, on a graphical user interface, an entity type selector configured to receive a selection of one of multiple different entities for a type of financial analysis;   receiving, from the entity type selector, a selection of an a first entity;   accessing, from at least one of a plurality of raw data repositories, stored raw data associated with the selected first entity, wherein the stored raw data includes financial transaction data records, wherein the raw data repositories are configured for the storage of raw data associated with multiple different entities;   presenting, on the graphical user interface, an analysis type selector configured to receive a selection of one of multiple different types of financial analyses, wherein the multiple different types of financial analyses includes:
 a fraud analysis type configured to analyze the stored raw data to perform fraud detection for a selected entity, and 
 a non-fraud analysis type configured to analyze the stored raw data to generate information that is not related to fraud detection for a selected entity; 
   receiving, from the analysis type selector, a section for the non-fraud analysis type of financial analysis; and   performing, on a processing unit, the non-fraud analysis type of financial analysis to generate information that is not related to fraud detection for the first entity.   
     
     
         11 . The computer-program product of  claim 1 , wherein the non-fraud analysis type of analysis further facilitates predicting an attrition score with respect to the first entity, and wherein the information includes an attrition score for the first entity. 
     
     
         12 . The computer-program product of  claim 2 , wherein the first entity is a merchant engaged in a customer relationship with a financial service provider, and wherein the attrition score indicates a likelihood the customer relationship will cease. 
     
     
         13 . The computer-program product of  claim 12 , wherein the financial service provider applies a fee structure to the first entity, and wherein the accessed raw data includes information that represents the fee structure, and wherein the attrition score is based on the information that represents the fee structure. 
     
     
         14 . The computer-program product of  claim 12 , wherein the accessed raw data includes a data record that indicates a history of payments made by the first entity to the financial service provider, and wherein the attrition score is based on the accessed data record. 
     
     
         15 . The computer-program product of  claim 14 , wherein the data record further indicates timeliness of the payments. 
     
     
         16 . The computer-program product of  claim 15 , further comprising:
 receiving a selection of a second entity, wherein the selection of the second entity is inputted using the entity type selector, and wherein the second entity is an individual account holder who maintains an account serviced by the financial service provider;   receiving a selection of the fraud detection analysis type of analysis, wherein the selection of the fraud detection analysis type of analysis is inputted using the analysis type selector;   accessing raw data associated with transactional activity involving the account; and   detecting fraud involving the account, wherein detecting fraud includes analyzing the raw data associated with the transactional activity by applying the fraud detection analysis type of analysis.   
     
     
         17 . The computer-program product of  claim 16 , wherein the raw data associated with the transactional activity is accessed from another of the plurality of raw data depositories, and wherein the plurality of raw data depositories are maintained in a distributed environment. 
     
     
         18 . The computer-program product of  claim 10 , further comprising:
 receiving a selection of the fraud detection analysis type of financial analysis, wherein the selection of the fraud detection analysis type is inputted using the analysis type selector;   in response to receiving the selection of the fraud detection analysis type, accessing additional raw data associated with the first entity, wherein the additional raw data includes data representing transactional activities involving multiple types of credit cards; and   detecting fraud involving the first entity, wherein detecting fraud includes analyzing the additional raw data using the fraud detection analysis type of financial analysis, and wherein detecting fraud includes calculating an incidence of fraud amongst transactions involving the first entity.   
     
     
         19 . A system comprising:
 a processor configured to perform operations including:   presenting, on a graphical user interface, an entity type selector configured to receive a selection of one of multiple different entities for a type of financial analysis;   receiving, from the entity type selector, a selection of an a first entity;   accessing, from at least one of a plurality of raw data repositories, stored raw data associated with the selected first entity, wherein the stored raw data includes financial transaction data records, wherein the raw data repositories are configured for the storage of raw data associated with multiple different entities;   presenting, on the graphical user interface, an analysis type selector configured to receive a selection of one of multiple different types of financial analyses, wherein the multiple different types of financial analyses includes:
 a fraud analysis type configured to analyze the stored raw data to perform fraud detection for a selected entity, and 
 a non-fraud analysis type configured to analyze the stored raw data to generate information that is not related to fraud detection for a selected entity; 
   receiving, from the analysis type selector, a section for the non-fraud analysis type of financial analysis; and   performing, on a processing unit, the non-fraud analysis type of financial analysis to generate information that is not related to fraud detection for the first entity.   
     
     
         20 . The system of  claim 19 , wherein the non-fraud analysis type of analysis further facilitates predicting an attrition score with respect to the first entity, and wherein the information includes an attrition score for the first entity. 
     
     
         21 . The system of  claim 20 , wherein the first entity is a merchant engaged in a customer relationship with a financial service provider, and wherein the attrition score indicates a likelihood the customer relationship will cease. 
     
     
         22 . The system of  claim 21 , wherein the financial service provider applies a fee structure to the first entity, and wherein the accessed raw data includes information that represents the fee structure, and wherein the attrition score is based on the information that represents the fee structure. 
     
     
         23 . The system of  claim 21 , wherein the accessed raw data includes a data record that indicates a history of payments made by the first entity to the financial service provider, and wherein the attrition score is based on the accessed data record. 
     
     
         24 . The system of  claim 23 , wherein the data record further indicates timeliness of the payments. 
     
     
         25 . The system of  claim 24 , further comprising:
 receiving a selection of a second entity, wherein the selection of the second entity is inputted using the entity type selector, and wherein the second entity is an individual account holder who maintains an account serviced by the financial service provider;   receiving a selection of the fraud detection analysis type of analysis, wherein the selection of the fraud detection analysis type of analysis is inputted using the analysis type selector;   accessing raw data associated with transactional activity involving the account; and   detecting fraud involving the account, wherein detecting fraud includes analyzing the raw data associated with the transactional activity by applying the fraud detection analysis type of analysis.   
     
     
         26 . The system of  claim 25 , wherein the raw data associated with the transactional activity is accessed from another of the plurality of raw data depositories, and wherein the plurality of raw data depositories are maintained in a distributed environment. 
     
     
         27 . The system of  claim 19 , further comprising:
 receiving a selection of the fraud detection analysis type of financial analysis, wherein the selection of the fraud detection analysis type is inputted using the analysis type selector;   in response to receiving the selection of the fraud detection analysis type, accessing additional raw data associated with the first entity, wherein the additional raw data includes data representing transactional activities involving multiple types of credit cards; and detecting fraud involving the first entity, wherein detecting fraud includes analyzing the additional raw data using the fraud detection analysis type of financial analysis, and wherein detecting fraud includes calculating an incidence of fraud amongst transactions involving the first entity.