Computer-based collective intelligence recommendations for transaction review

Abstract

In an embodiment, a data processing method comprises obtaining a plurality of first transaction data items for a proposed online credit card purchase transaction that has been recommended for review; obtaining a plurality of second transaction data items for a set of similar past online credit card purchase transactions, wherein each member of the set has one or more transaction feature values that are similar to the transaction data items of the proposed online credit card purchase transaction, and a decision value specifying whether the member was accepted or rejected by a reviewer; obtaining a stored data model of features, feature values, transaction acceptance decisions and rejection decisions of the reviewer based at least in part on the set, determining, based on applying the first transaction data items to the stored data model and a subsequent query to the database among more recent transactions that were not included during model construction, a likelihood value of a particular decision of whether the proposed online credit card purchase transaction would be accepted or rejected by the reviewer of the merchant; causing the likelihood value to be displayed; wherein the method is performed by one or more computing devices.

1 . A method comprising:
 obtaining a plurality of first transaction data items for a proposed online credit card purchase transaction that has been recommended for review;   obtaining a plurality of second transaction data items for a set of similar past online credit card purchase transactions, wherein each member of the set has one or more transaction feature values that are similar to transaction feature values of the plurality of first transaction data items for the proposed online credit card purchase transaction, and a decision value specifying whether the member was accepted or rejected by a reviewer;   obtaining a stored data model of features, feature values, transaction acceptance decisions and rejection decisions of the reviewer, wherein the stored data model is based at least in part on the set of similar past online credit card purchase transactions;   determining, by a processor, based on applying the first transaction data items to the stored data model, a likelihood value of a particular decision of whether the proposed online credit card purchase transaction would be accepted or rejected by the reviewer of the merchant; and   causing the likelihood value to be displayed.   
     
     
         2 . The method of  claim 1 , further comprising recording the particular decision of whether the proposed online credit card transaction was accepted or rejected by the reviewer of the merchant. 
     
     
         3 . The method of  claim 2 , further comprising based at least part on the recorded particular decision, updating the stored data model. 
     
     
         4 . The method of  claim 1 , further comprising causing to be displayed at least one or more transaction feature values of one or more members of the set of similar past online credit card purchase transactions. 
     
     
         5 . The method of  claim 1 , wherein the stored data model includes a hierarchical decision tree. 
     
     
         6 . The method of  claim 5 , wherein the hierarchical decision tree is represented using XML. 
     
     
         7 . The method of  claim 5 , wherein nodes of the hierarchical decision tree represent transaction features and branches of the hierarchical decision tree represent transaction feature values. 
     
     
         8 . The method of  claim 5 , further comprising removing transaction features from a set of available candidate features based at least in part on transaction rejection data values. 
     
     
         9 . The method of  claim 5 , further comprising combining transaction features from a set of available candidate features based at least in part on an association among data values of the candidate transaction features. 
     
     
         10 . The method of  claim 7 , wherein a transaction feature is selected as a node of the hierarchical decision tree based at least in part on a contingency table comprising counts of historical transaction data for the transaction feature. 
     
     
         11 . The method of  claim 7 , wherein a transaction feature is selected as a node of the hierarchical decision tree based at least in part on a relative entropy measure determined from the contingency table. 
     
     
         12 . A non-transitory computer-readable medium carrying one or more sequences of instructions, which when executed by one or more processors, cause the one or more processors to carry out the steps of:
 obtaining a plurality of first transaction data items for a proposed online credit card purchase transaction that has been recommended for review;   obtaining a plurality of second transaction data items for a set of similar past online credit card purchase transactions, wherein each member of the set has one or more transaction feature values that are similar to the transaction data items of the proposed online credit card purchase transaction, and a decision value specifying whether the member was accepted or rejected by a reviewer;   obtaining a stored data model of features, feature values, transaction acceptance decisions and rejection decisions of the reviewer based at least in part on the set;   determining, based on applying the first transaction data items to the stored data model, a likelihood value of a particular decision of whether the proposed online credit card purchase transaction would be accepted or rejected by the reviewer of the merchant; and   causing the likelihood value to be displayed.   
     
     
         13 . The non-transitory computer-readable medium of  claim 12 , further comprising instructions which, when executed by the one or more processors, cause the one or more processors to record the particular decision of whether the proposed online credit card transaction was accepted or rejected by the reviewer of the merchant. 
     
     
         14 . The non-transitory computer-readable medium of  claim 13 , further comprising instructions which, when executed by the one or more processors, cause the one or more processors to, based at least part on the recorded particular decision, update the stored data model. 
     
     
         15 . The non-transitory computer-readable medium of  claim 12 , further comprising instructions which, when executed by the one or more processors, cause the one or more processors to display at least one or more transaction feature values of one or more members of the set of similar past online credit card purchase transactions. 
     
     
         16 . The non-transitory computer-readable medium of  claim 12 , wherein the stored data model includes a hierarchical decision tree. 
     
     
         17 . The non-transitory computer-readable medium of  claim 16 , wherein the hierarchical decision tree is represented using XML. 
     
     
         18 . The non-transitory computer-readable medium of  claim 16 , wherein nodes of the hierarchical decision tree represent transaction features and branches of the hierarchical decision tree represent transaction feature values. 
     
     
         19 . The non-transitory computer-readable medium of  claim 16 , further comprising instructions which, when executed by the one or more processors, cause the one or more processors to remove transaction features from a set of available candidate features based at least in part on transaction rejection data values. 
     
     
         20 . The non-transitory computer-readable medium of  claim 16 , further comprising instructions which, when executed by the one or more processors, cause the one or more processors to combine transaction features from a set of available candidate features based at least in part on an association among data values of the candidate transaction features. 
     
     
         21 . The non-transitory computer-readable medium of  claim 18 , wherein a transaction feature is selected as a node of the hierarchical decision tree based at least in part on a contingency table comprising counts of historical transaction data for the transaction feature. 
     
     
         22 . The non-transitory computer-readable medium of  claim 18 , wherein a transaction feature is selected as a node of the hierarchical decision tree based at least in part on a relative entropy measure determined from the contingency table.