Leakage detection system

Abstract

The present disclosure include an exemplary method comprising receiving a transaction history comprising transaction information associated with a plurality of transactions for an entity, wherein the transaction information involves transactions completed between employees of the entity and one or more merchants; detecting, using a machine learning algorithm, one or more leakage events associated with a transaction, the one or more leakage events comprising a first leakage event, wherein the first leakage event indicates a non-compliance of a spending rule of the entity by a participant in the transaction, wherein the one or more detected leakage events are analyzed as inputs to improve performance of the machine learning algorithm using unsupervised machine learning; and performing an analysis of a compliance level of the entity based on performing the detection of the one or more leakage events for the plurality of transactions.

What is claimed is: 
     
         1 . A method comprising:
 receiving, by a computing device of a transaction account issuer, a transaction history comprising transaction information associated with a plurality of transactions for an entity, wherein the transaction information involves transactions completed between employees of the entity and one or more merchants, wherein the transaction information is maintained in a transaction database of the transaction account issuer;   detecting, using a machine learning algorithm by the computing device, one or more leakage events associated with a transaction, the one or more leakage events comprising a first leakage event, wherein the first leakage event indicates a non-compliance of a spending rule of the entity by a participant in the transaction, wherein the one or more detected leakage events are analyzed as inputs to improve performance of the machine learning algorithm using unsupervised machine learning;   performing, by the computing device, an analysis of a compliance level of the entity based on performing the detection of the one or more leakage events for the plurality of transactions; and   outputting, to a network-based graphical user interface by the computing device on a display device, a compliance level of the entity that indicates an amount of employees of the entity that have been detected to participate in leakage events.   
     
     
         2 . The method of  claim 1 , wherein the detecting the one or more leakage events further comprises determining, by the computing device, a transaction purpose of the transaction, wherein the first leakage event is detected in further response to the transaction purpose being determined as having a personal purpose. 
     
     
         3 . The method of  claim 1 , further comprising:
 identifying, by the computing device, a merchant associated with the transaction by matching a merchant identifier in the transaction with stored merchant information associated with the merchant;   determining, by the computing device, if the identified merchant accepts a set payment method, wherein the first leakage event is detected in response to the identified merchant accepting or not accepting the set payment method.   
     
     
         4 . The method of  claim 2 , further comprising:
 comparing, by the computing device, a merchant identifier in the transaction with stored merchant information associated with a merchant;   determining, by the computing device, a confidence score in response to matching the merchant identifier with the stored merchant information using string distance calculations;   comparing, by the computing device, the confidence score to a confidence score threshold; and   identifying, by the computing device, the merchant as being associated with the transaction in response to the confidence score meeting or exceeding the confidence score threshold.   
     
     
         5 . The method of  claim 1 , further comprising:
 analyzing, by the computing device, consumer information associated with a consumer in the transaction, wherein the consumer information is comprised in the transaction information associated with the transaction;   matching, by the computing device, a consumer identifier comprised in the consumer information with stored consumer information associated with a stored consumer;   identifying, by the computing device, the consumer associated with the transaction; and   determining, by the computing device, if the consumer has been issued a predefined payment instrument to conduct a payment to complete the transaction, wherein the first leakage event is detected further in response to at least one of consumer not having been issued the predefined payment instrument.   
     
     
         6 . The method of  claim 1 , wherein the one or more leakage events comprise the first leakage event and a second leakage event, wherein the first leakage event comprises the transaction not being paid using a predefined payment method, wherein the second leakage event comprises the transaction being identified as having a personal purpose. 
     
     
         7 . The method of  claim 1 , wherein the one or more leakage events comprises the first leakage event and a second leakage event, wherein the first leakage event comprises the transaction not being paid using a predefined payment method, wherein the first leakage event is identified as having a business purpose, wherein the second leakage event comprises merchant information associated with the transaction as being incomplete, wherein the method further comprises supplying incomplete information from previously stored merchant information by matching available merchant information associated with the transaction with the previously stored merchant information. 
     
     
         8 . The method of  claim 7 , wherein the matching of the available merchant information associated with the transaction with the previously stored merchant information comprises determining, by the computing device, a confidence score in response to matching the available merchant information with the previously stored merchant information using string distance calculations;
 comparing, by the computing device, the confidence score to a confidence score threshold; and   identifying, by the computing device, the available merchant information as being associated with the previously stored merchant information in response to the confidence score meeting or exceeding the confidence score threshold.   
     
     
         9 . The method of  claim 1 , further comprising presenting on a graphical display, by the computing device, one or more possible action items to address the detected one or more leakage events. 
     
     
         10 . A system comprising:
 a computing device comprising a processor; and   a non-transitory memory configured to communicate with the processor, the non-transitory memory having instructions stored thereon that, in response to execution by the processor, cause the computing device to:
 receive a transaction history comprising transaction information associated with a plurality of transactions for an entity, wherein the transaction information involves transactions completed between employees of the entity and one or more merchants, wherein the transaction information is maintained in a transaction database of a transaction account issuer; 
 detect, using a machine learning algorithm, one or more leakage events associated with a transaction, the one or more leakage events comprising a first leakage event, wherein the first leakage event indicates a non-compliance of a spending rule of the entity by a participant in the transaction, wherein the one or more detected leakage events are analyzed as inputs to improve performance of the machine learning algorithm using unsupervised machine learning; 
 perform an analysis of a compliance level of the entity based on performing the detection of the one or more leakage events for the plurality of transactions; and 
 output, to a network-based graphical user interface, a compliance level of the entity that indicates an amount of employees of the entity that have been detected to participate in leakage events. 
   
     
     
         11 . The system of  claim 10 , wherein the detecting the one or more leakage events further comprises determining a transaction purpose of the transaction, wherein the first leakage event is detected in further response to the transaction purpose being determined as having a personal purpose. 
     
     
         12 . The system of  claim 10 , wherein the instructions further cause the computing device to:
 identify a merchant associated with the transaction by matching a merchant identifier in the transaction with stored merchant information associated with the merchant;   determine if the identified merchant accepts a set payment method, wherein the first leakage event is detected in response to the identified merchant accepting or not accepting the set payment method.   
     
     
         13 . The system of  claim 12 , wherein the instructions further cause the computing device to:
 compare a merchant identifier in the transaction with stored merchant information associated with a merchant;   determine a confidence score in response to matching the merchant identifier with the stored merchant information using string distance calculations;   compare the confidence score to a confidence score threshold; and   identify the merchant as being associated with the transaction in response to the confidence score meeting or exceeding the confidence score threshold.   
     
     
         14 . The system of  claim 10 , wherein the instructions further cause the computing device to:
 analyze consumer information associated with a consumer in the transaction, wherein the consumer information is comprised in the transaction information associated with the transaction;   match a consumer identifier comprised in the consumer information with stored consumer information associated with a stored consumer;   identify the consumer associated with the transaction; and   determine if the consumer has been issued a predefined payment instrument to conduct a payment to complete the transaction, wherein the first leakage event is detected further in response to at least one of consumer not having been issued the predefined payment instrument.   
     
     
         15 . The system of  claim 10 , wherein the one or more leakage events comprises the first leakage event and a second leakage event, wherein the first leakage event comprises the transaction not being paid using a predefined payment method, wherein the second leakage event comprises the transaction being identified as having a personal purpose. 
     
     
         16 . The system of  claim 10 , wherein the one or more leakage events comprise the first leakage event and a second leakage event, wherein the first leakage event comprises the transaction not being paid using a predefined payment method, wherein the first leakage event is identified as having a business purpose, wherein the second leakage event comprises merchant information associated with the transaction as being incomplete, wherein the method further comprises supplying incomplete information from previously stored merchant information by matching available merchant information associated with the transaction with the previously stored merchant information. 
     
     
         17 . The system of  claim 16 , wherein the matching of the available merchant information associated with the transaction with the previously stored merchant information comprises:
 determining, by the computing device, a confidence score in response to matching the available merchant information with the previously stored merchant information using string distance calculations;   comparing, by the computing device, the confidence score to a confidence score threshold; and   identifying, by the computing device, the available merchant information as being associated with the previously stored merchant information in response to the confidence score meeting or exceeding the confidence score threshold.   
     
     
         18 . The system of  claim 10 , wherein the instructions further cause the computing device to present on the network-based graphical user interface by the computing device, one or more possible action items to address the detected one or more leakage events. 
     
     
         19 . A non-transitory computer readable storage medium having instructions stored thereon that, in response to execution by a processor of a computing device, cause the computing device to perform operations comprising:
 receiving a transaction history comprising transaction information associated with a plurality of transactions for an entity, wherein the transaction information involves transactions completed between employees of the entity and one or more merchants, wherein the transaction information is maintained in a transaction database of a transaction account issuer;   detecting, using a machine learning algorithm, one or more leakage events associated with a transaction, the one or more leakage events comprising a first leakage event, wherein the first leakage event indicates a non-compliance of a spending rule of the entity by a participant in the transaction, wherein the one or more detected leakage events are analyzed as inputs to improve performance of the machine learning algorithm using unsupervised machine learning;   performing an analysis of a compliance level of the entity based on performing the detection of the one or more leakage events for the plurality of transactions; and   outputting, to a network-based graphical user interface, a compliance level of the entity that indicates an amount of employees of the entity that have been detected to participate in leakage events.   
     
     
         20 . The non-transitory computer readable storage medium of  claim 19 , wherein the instructions further cause the computing device to present on the network-based graphical user interface by the computing device, one or more possible action items to address the detected one or more leakage events.