In the area of credit risk analytics, current Bankruptcy Prediction Models (BPMs) struggle with (a) the availability of comprehensive and real-world data sets and (b) the presence of extreme class imbalance in the data (i.e., very few samples for the minority class) that degrades the performance of the prediction model. Moreover, little research has compared the relative performance of well-known BPM's on public datasets addressing the class imbalance problem. In this work, we apply eight classes of well-known BPMs, as suggested by a review of decades of literature, on a new public dataset named Freddie Mac Single-Family Loan-Level Dataset with resampling (i.e., adding synthetic minority samples) of the minority class to tackle class imbalance. Additionally, we apply some recent AI techniques (e.g., tree-based ensemble techniques) that demonstrate potentially better results on models trained with resampled data. In addition, from the analysis of 19 years (1999-2017) of data, we discover that models behave differently when presented with sudden changes in the economy (e.g., a global financial crisis) resulting in abrupt fluctuations in the national default rate. In summary, this study should aid practitioners/researchers in determining the appropriate model with respect to data that contains a class imbalance and various economic stages.
Fannie Mae, the nation's largest source of conventional mortgage funds, has made a commitment to use technology to improve the efficiency of processing a loan by reducing the time, paperwork and cost associated with loan origination. The Desktop Underwriter (DU) system which was developed as a result of this commitment, is an automated underwriting expert system that applies both heuristics and statistics to the problem. The system supports both the wholesale and retail mortgage environments and is built to reason and underwrite loans with incomplete, unverified and conflicting data. The system generates a credit recommendation based on the loan's conformity to credit standards and an eligibility recommendation based on the loan's conformity to eligibility
The GENIUS Automated Underwriting System is an expert advisor that has been in successful nationwide production by GE Mortgage Insurance Corporation for two years to underwrite mortgage insurance. The knowledge base was developed using a unique hybrid approach combining the best of traditional knowledge engineering and a novel machine learning method called Example Based Evidential Reasoning (EBER). As one indicator of the effkacy of this approach, a complex system was completed in 11 months that achieved a 98% agreement rate with practicing underwriters for approve recommendations in the fist month of operation. This performance and numerous additional business benefits have now been confirmed by two full years of nationwide production during which time some 800,000 applications have been underwritten. As a result of this outstanding success, the GENIUS system is serving as the basis for a major re-engineering of the underwriting process within the business. Also, a new version has recently been announced as an external product to bring the benefits of this technology to the mortgage industry at large. In addition, the concepts and methodology are being applied to other financial services applications such as commercial credit analysis and municipal bond credit enhancement. This paper documents the development process and operational results and concludes with a summary of critical success factors.
Custom DU is an automated underwriting system that enables mortgage lenders to build their own business rules that facilitate assessing borrower eligibility for different mortgage products. Developed by Fannie Mae, Custom DU has been used since 2004 by several lenders to automate the underwriting of numerous mortgage products. Custom DU uses rule specification language techniques and a web-based, user-friendly interface for implementing business rules that represent business policy. By means of the user interface, lenders can also customize their underwriting findings reports, test the rules that they have defined, and publish changes to business rules on a real-time basis, all without any software modifications. The user interface enforces structure and consistency, enabling business users to focus on their underwriting guidelines when converting their business policy to rules. Once lenders have created their rules, loans are routed to the appropriate rule sets, and customized, but consistent, results are always returned to the lender. Using Custom DU, lenders can create different rule sets for their products and assign them to different channels of the business, allowing for centralized control of underwriting policies and procedures—even if lenders have decentralized operations.
Countrywide Loan Underwriting Expert System (CLUEZP) is an advanced, automated mortgage underwriting rule-based expert system. The system was developed to increase the production capacity and productivity of Countrywide branches, improve the consistency of underwriting, and reduce the cost of originating a loan. The system receives selected information from the loan application, credit report, and appraisal. It then decides whether the loan should be approved or whether it requires further review by a human underwriter. If the system approves the loan, no further review is required and the application is funded. CLUES has been in production since February 1993, and is currently processing more than 8500 loans per month in over 300 decentralized branches around the country.