System and method of detecting and assessing multiple types of risks related to mortgage lending

Abstract

Embodiments include systems and methods of detecting and assessing multiple types of risks related to mortgage lending. One embodiment includes a system and method of detecting and assessing risks including fraud risks, early payment default risks, and risks related to fraudulently stated income on loan applications. One embodiment includes a computerized method that includes creating a combined risk detection model based on a plurality of risk detection models and using the combined risk detection model to evaluate loan application data and generate a combined risk score that takes into account interaction of different types of risks individually and collectively detected by the plurality of risk detection models.

What is claimed is: 
     
         1 . A system for detecting and assessing risks, the system comprising:
 a computer system comprising one or more computing devices, the computer system programmed, via executable code modules, to implement:   a combined risk detection model for detecting and assessing a plurality of risks in data, the combined risk detection model configured to receive as input a plurality of input features extracted from two or more of a plurality of risk detection models, the plurality of risk detection models comprising:
 a first risk detection model configured to generate a first risk model score that is indicative of the presence of a first risk in the data; 
 a second risk detection model configured to generate a second risk model score that is indicative of the presence of a second risk in the data; and 
 a third risk detection model configured to generate a third risk model score that is indicative of the presence of a third risk in the data, wherein the first risk detection model, the second risk detection model, and the third risk detection model are different models, 
   wherein the computer system is further programmed to:
 determine combinability of the plurality of risk detection models based at least partly on evaluating predictive performance of scores from one or more combinations of the risk detection models against historical data; 
 extract input features from the risk detection models that are determined to be combinable for input into the combined risk detection model, the input features selected based at least in part on an identified interaction between the scores from the plurality of risk detection models, or an identified interaction between respective scores from the plurality of risk detection models and other input fields outside a scope of the respective risk detection model; and 
 generate a composite risk score based at least in part on calibrated scores from the models determined to be combinable and the extracted input features; and 
   an output module that outputs the composite risk score generated by the combined risk detection model and one or more risk indicators to indicate individual risk factors that contributed to the composite risk score.   
     
     
         2 . The system of  claim 1 , wherein the data comprises loan application data. 
     
     
         3 . The system of  claim 2 , wherein the output module further outputs one or more recommendations for corrective action in view of any risks. 
     
     
         4 . The system of  claim 1 , wherein the first risk detection model comprises a fraud model, and wherein the second risk detection model comprises a fraud model. 
     
     
         5 . The system of  claim 1 , wherein the first risk detection model comprises a default risk model, and wherein the second risk detection model comprises a default risk model. 
     
     
         6 . The system of  claim 1 , wherein the first risk detection model comprises a fraud model, wherein the second risk detection model comprises a multi-component risk model, and wherein the third risk detection model comprises a default risk model. 
     
     
         7 . The system of  claim 1 , wherein a modeling method used to construct the combined risk detection model comprises one of: linear regression, logical regression, neural networks, support vector machines, or decision trees generated using a machine learning algorithm that uses a tree-like graph to predict an outcome. 
     
     
         8 . The system of  claim 1 , wherein the plurality of risk detection models are generated based at least in part on segmentation of the historical data. 
     
     
         9 . The system of  claim 8 , wherein the segmentation corresponds to geographic characteristics associated with the historical data. 
     
     
         10 . The system of  claim 8 , wherein the segmentation corresponds to a clustering analysis of the historical data. 
     
     
         11 . The system of  claim 1 , wherein the risks comprise lending risks. 
     
     
         12 . The system of  claim 1 , wherein the first risk detection model comprises an income fraud model. 
     
     
         13 . A computerized method of detecting and assessing risks, the method comprising:
 receiving, on a physical computer processor, data and historical data;   determining, on a physical computer processor, combinability of a plurality of risk detection models, the determining comprising determining predictive performance of scores from one or more combinations of the risk detection models as compared to the historical data, wherein the plurality of risk detection models further comprise two or more of:
 a first risk detection model configured to generate a first risk model score that is indicative of the presence of a first risk in the data; 
 a second risk detection model configured to generate a second risk model score that is indicative of the presence of a second risk in the data; or 
 a third risk detection model configured to generate a third risk model score that is indicative of the presence of a third risk in the data, wherein the first risk detection model, the second risk detection model, and the third risk detection model are different models; 
   extracting, on a physical computer processor, input features from the risk detection models that are determined to be combinable for input into a combined risk detection model, the input features being selected based at least in part on an identified interaction between the scores from the plurality of risk detection models, or an interaction between respective scores from the plurality of risk detection models and other input fields outside a scope of the respective risk detection model;   applying, on a physical computer processor, the combined risk detection model to the data to generate a composite risk score; and   generating, on a physical computer processor, an output including the composite risk score generated by the combined risk detection model and one or more risk indicators to indicate individual risk factors that contributed to the composite risk score.   
     
     
         14 . The method of  claim 13 , wherein the determining of the combinability of the plurality of risk detection models is based at least in part on the correlation of the results of applying the plurality of risk detection models to historical data. 
     
     
         15 . The method of  claim 14 , wherein the correlation is based at least in part on a measure of the similarity of the results among the plurality of risk detection models. 
     
     
         16 . The method of  claim 13 , wherein the input features are selected by:
 applying each of the plurality of risk detection models to data to generate a score for each risk detection model, the data comprising historical mortgage transaction data;   identifying an interaction among scores from the plurality of risk detection models; and   using the interaction as a basis for the selection of the input features.   
     
     
         17 . The method of  claim 13 , wherein the input features are selected by:
 applying each of the plurality of risk detection models to data to generate a score for each risk detection model, the data comprising historical mortgage transaction data;   performing a swap analysis on the scores from applying the plurality of risk detection models to the data; and   using the result of the swap analysis as a basis for the selection of the input features.   
     
     
         18 . The method of  claim 13 , wherein the first risk detection model comprises a fraud model, and wherein the second risk detection model comprises a fraud model. 
     
     
         19 . The method of  claim 13 , wherein the first risk detection model comprises a default risk model, and wherein the second risk detection model comprises a default risk model. 
     
     
         20 . The method of  claim 13 , wherein the plurality of risk detection models are generated based at least in part on segmentation of the historical transactions data.