Aggregation based credit decision

Abstract

Apparatuses, systems, methods, and computer program products are disclosed for aggregation based credit decisions. An apparatus includes a data module configured to receive transaction data for a user that is aggregated from a plurality of different third-party data sources where the user has accounts. An apparatus includes an analysis module configured to analyze aggregated transaction data using machine learning to determine a credit metric describing a credit worthiness of a user. An apparatus includes a credit module configured to provide a determined credit metric to one or more interested third parties.

1 . An apparatus, comprising:
 a data module configured to receive transaction data for a user that is aggregated from a plurality of different third-party data sources where the user has accounts;   an analysis module configured to analyze the aggregated transaction data using machine learning to determine a credit metric describing a credit worthiness of the user; and   a credit module configured to provide the determined credit metric to one or more interested third parties.   
     
     
         2 . The apparatus of  claim 1 , wherein the machine learning executes a clustering algorithm for grouping a plurality of users based on aggregated transaction data for each of the plurality of users. 
     
     
         3 . The apparatus of  claim 2 , wherein the analysis module is further configured to determine a credit metric for the grouping of the plurality of users based on the aggregated transaction data for each of the plurality of users. 
     
     
         4 . The apparatus of  claim 1 , further comprising a trend module configured to determine one or more trends in the user's aggregated transaction data that describes one or more tendencies of the user over time, the credit metric determined at least in part on the one or more trends. 
     
     
         5 . The apparatus of  claim 4 , wherein the trend module is further configured to:
 group one or more merchants in the user's aggregated transaction data based on one or more characteristics of the merchants; and   determine whether the trends in the user's aggregated transaction data indicate that the user's spending has changed from one group of merchants to a different group of merchants, the credit metric determined at least in part on the user's changed spending.   
     
     
         6 . The apparatus of  claim 5 , wherein the trend module is further configured to determine whether one of the user's debt and the user's savings has one of increased and decreased in relation to the user's spending at the one or more groups of merchants, the credit metric determined at least in part on the user's debt and savings levels in relation to the user's spending at the one or more groups of merchants. 
     
     
         7 . The apparatus of  claim 4 , wherein the analysis module is further configured to provide data for the trends in the user's aggregated transaction data to the machine learning to generate projections for future trend data for the user and determine the credit metric for the user based at least in part on the future trend data. 
     
     
         8 . The apparatus of  claim 4 , wherein the machine learning executes a clustering algorithm for grouping a plurality of users based on trends in each of the users aggregated transaction data, the credit metric determined for the grouping of the plurality of users determined at least in part on the trends. 
     
     
         9 . The apparatus of  claim 8 , wherein the analysis module is further configured to dynamically adjust the credit metric, using machine learning, for the grouping of the plurality of users in response to detecting a change in the trends in each of the users aggregated transaction data. 
     
     
         10 . The apparatus of  claim 1 , wherein the aggregated transaction data comprises financial data, the financial data comprising one or more of financial transaction data, investment data, savings data, and debt data, the machine learning generating the credit metric for the user based at least in part on the financial data. 
     
     
         11 . A method, comprising:
 receiving transaction data for a user that is aggregated from a plurality of different third-party data sources where the user has accounts;   analyzing the aggregated transaction data using machine learning to determine a credit metric describing a credit worthiness of the user; and   providing the determined credit metric to one or more interested third parties.   
     
     
         12 . The method of  claim 11 , wherein the machine learning executes a clustering algorithm for grouping a plurality of users based on aggregated transaction data for each of the plurality of users. 
     
     
         13 . The method of  claim 12 , wherein the analysis module is further configured to determine a credit metric for the grouping of the plurality of users based on the aggregated transaction data for each of the plurality of users. 
     
     
         14 . The method of  claim 11 , further comprising determining one or more trends in the user's aggregated transaction data that describes one or more tendencies of the user over time, the credit metric determined at least in part on the one or more trends. 
     
     
         15 . The method of  claim 14 , further comprising:
 grouping one or more merchants in the user's aggregated transaction data based on one or more characteristics of the merchants; and   determining whether the trends in the user's aggregated transaction data indicate that the user's spending has changed from one group of merchants to a different group of merchants, the credit metric determined at least in part on the user's changed spending.   
     
     
         16 . The method of  claim 15 , further comprising determining whether one of the user's debt and the user's savings has one of increased and decreased in relation to the user's spending at the one or more groups of merchants, the credit metric determined at least in part on the user's debt and savings levels in relation to the user's spending at the one or more groups of merchants. 
     
     
         17 . The method of  claim 14 , further comprising providing data for the trends in the user's aggregated transaction data to the machine learning to generate projections for future trend data for the user and determine the credit metric for the user based at least in part on the future trend data. 
     
     
         18 . The method of  claim 14 , wherein the machine learning executes a clustering algorithm for grouping a plurality of users based on trends in each of the users aggregated transaction data, the credit metric determined for the grouping of the plurality of users determined at least in part on the trends. 
     
     
         19 . The method of  claim 18 , further comprising dynamically adjusting the credit metric, using machine learning, for the grouping of the plurality of users in response to detecting a change in the trends in each of the users aggregated transaction data. 
     
     
         20 . An apparatus, comprising:
 means for receiving transaction data for a user that is aggregated from a plurality of different third-party data sources where the user has accounts;   means for analyzing the aggregated transaction data using machine learning to determine a credit metric describing a credit worthiness of the user; and   means for providing the determined credit metric to one or more interested third parties.