System for generating scores related to interactions with a revenue generator

Abstract

A system for generating scores related to interactions with a revenue generator. A historical dataset corresponding to a historical behavior of a set of revenue generators may be identified. The historical dataset may be processed to identify a feature vector. A classifier model may be generated from the historical dataset and the feature vector. Current revenue generator data representing a current revenue generator may be collected. The current revenue generator data may be processed to generate a current revenue generator feature vector. A score may be generated by applying the classifier model to the current revenue generator data feature vector.

1 . A method for generating scores related to interactions with a revenue generator, comprising:
 identifying a historical dataset corresponding to a historical behavior of a set of revenue generators;   processing the historical dataset to identify a feature vector wherein the feature vector comprises a set of variables related to detecting a fraudulent revenue generator;   generating a classifier model from the historical dataset and the feature vector;   collecting current revenue generator data representing a current revenue generator;   processing the current revenue generator data to generate a current revenue generator data feature vector; and   generating a score by applying the classifier model to the current revenue generator data feature vector, wherein the score represents a likelihood of the current revenue generator committing fraud.   
     
     
         2 . The method of  claim 1  wherein generating the classifier model further comprises inputting the historical dataset and the feature vector to a machine learning algorithm to generate the classifier model. 
     
     
         3 . The method of  claim 2  wherein the machine learning algorithm comprises a decision tree. 
     
     
         4 . The method of  claim 1  wherein generating the score further comprises:
 generating a scoring metric; and   applying the scoring metric to the score generated by the classifier model.   
     
     
         5 . The method of  claim 4  wherein the scoring metric comprises a multiplier. 
     
     
         6 . The method of  claim 5  wherein the multiplier is 1000. 
     
     
         7 . The method of  claim 1  where in the historical behavior of the set of revenue generators is identified as fraudulent behavior or not fraudulent behavior. 
     
     
         8 . The method of  claim 1  wherein the feature vector comprises at least one of a spend history, a spend to replenish ratio, an average amount of payment, a number of times a credit card is charged in a month, a total sum of charges accrued in a month, an average adjustment amount, a total number of adjustments, a client tier value, a security status value, a risk status value, a client age value, a client search term max-spend-score, a client search term risk score, a client search term risk-spend score, a client max spend over daily budget score, a client run rate over daily budget score, a client risk-run rate score, a client run-rate rate of change score, and a client card score. 
     
     
         9 . The method of  claim 1  further comprising:
 modifying the current revenue generator data to include a classification value;   adding the current revenue generator data to the historical revenue generator data;   re-processing the historical revenue generator data to generate the feature vector; and   re-generating the classifier model from the historical revenue generator data and the feature vector.   
     
     
         10 . The method of  claim 9  wherein the classification value identifies the revenue generator as a fraudulent revenue generator. 
     
     
         11 . The method of  claim 1  wherein the revenue generator comprises an online advertiser. 
     
     
         12 . A method of scoring a revenue generator, comprising:
 collecting a revenue generator data representing the revenue generator;   processing the revenue generator data; and   generating a score of the revenue generator data indicating the likelihood of the revenue generator being a fraudulent revenue generator.   
     
     
         13 . The method of  claim 12  wherein processing the revenue generator data further comprises processing the revenue generator data to identify a feature vector wherein the feature vector comprises a set of variables related to detecting revenue generator fraud. 
     
     
         14 . The method of  claim 12  wherein the feature vector comprises at least one of a spend history, a spend to replenish ratio, an average amount of payment, a number of times a credit card is charged in a month, a total sum of charges accrued in a month, an average adjustment amount, a total number of adjustments, a client tier value, a security status value, a risk status value, a client age value, a client search term max-spend-score, a client search term risk score, a client search term risk-spend score, a client max spend over daily budget score, a client run rate over daily budget score, a client risk-run rate score, a client run-rate rate of change score, and a client card score. 
     
     
         15 . The method of  claim 12  wherein generating the score further comprises inputting the feature vector to a classifier model. 
     
     
         16 . The method of  claim 15  wherein generating the score further comprises:
 generating a scoring metric; and   applying the scoring metric to the score generated by the classifier model.   
     
     
         17 . The method of  claim 16  wherein the scoring metric comprises a multiplier. 
     
     
         18 . A system for generating scores relating to interactions with a revenue generator, comprising:
 a memory to store a classifier model, a historical revenue generator dataset, a feature vector, a current revenue generator data and a current revenue generator data feature vector;   an interface operatively connected to the memory to collect the current revenue data from a current revenue generator;   a processor operatively connected to the memory and the interface, which processes the historical revenue generator dataset to identify the feature vector, generates the classifier model from the historical dataset and the feature vector, processes the current revenue generator data to generate the current revenue generator data feature vector, and generates a score signifying a likelihood of the current revenue generator committing fraud by applying the classifier model to the current revenue generator data feature vector.   
     
     
         19 . The system of  claim 18  wherein the processor generates a scoring metric and applies the scoring metric to the score generated by the classifier model. 
     
     
         20 . The system of  claim 18  wherein the classifier model is generated by using a machine learning algorithm. 
     
     
         21 . The system of  claim 20  wherein the machine learning algorithm comprises a decision tree. 
     
     
         22 . The system of  claim 18  wherein the feature vector comprises at least one of a spend history, a spend to replenish ratio, an average amount of payment, a number of times a credit card is charged in a month, a total sum of charges accrued in a month, an average adjustment amount, a total number of adjustments, a client tier value, a security status value, a risk status value, a client age value, a client search term max-spend-score, a client search term risk score, a client search term risk-spend score, a client max spend over daily budget score, a client run rate over daily budget score, a client risk-run rate score, a client run-rate rate of change score, and a client card score. 
     
     
         23 . The system of  claim 18  wherein the historical revenue generator data comprises data identified as relating to a fraudulent revenue generator and data identified as relating to a not fraudulent revenue generator.