Predicting Consumer Default: A Deep Learning Approach

Abstract

We develop a model to predict consumer default based on deep learning. We show that the model consistently outperforms standard credit scoring models, even though it uses the same data. Our model is interpretable and is able to provide a score to a larger class of borrowers relative to standard credit scoring models while accurately tracking variations in systemic risk. We argue that these properties can provide valuable insights for the design of policies targeted at reducing consumer default and alleviating its burden on borrowers and lenders, as well as macroprudential regulation. JEL Codes: C45; D14; E27; E44; G21; G24.in the United States. They are proprietary measures designed to rank borrowers based on their probability of future default. Specifically, they target the probability of a 90 days past due delinquency in the next 24 months. 1 Despite their ubiquitous use in the financial industry, there is very little information on credit scores, and emerging evidence suggests that as currently formulated credit scores have severe limitations. For example, Albanesi, De Giorgi, and Nosal (2017) show that during the 2007-2009 housing crisis there was a marked rise in mortgage delinquencies and foreclosures among high credit score borrowers, suggesting that credit scoring models at the time did not accurately reflect the probability of default for these borrowers. Additionally, it is well known that credit scores and indiscriminately low for young borrowers, and a substantial fraction of borrowers are unscored, which prevents them from accessing conventional forms of consumer credit.The Fair Credit Reporting Act, a legislation passed in 1970, and the Equal Opportunity in Credit Access Act of 1984 regulate credit scores and in particular determine which information can be included and must be excluded in credit scoring models. Such models can incorporate information in a borrower's credit report, except age and location. These restrictions are intended to prevent discrimination by age and factors related to location, such as race. 2 The law also mandates that entities that provide credit scores make public the four most important factors affecting scores. In marketing information, these are reported to be payment history, which is stated to explain about 35% of variation in credit scores, followed by amounts owed, length of credit history, new credit and credit mix, explaining 30%, 15%, 10% and 10% of the variation in credit scores respectively. Other than this, there is very little public information on credit scoring models, though several services are now available that allow consumers to simulate how various scenarios, such as paying off balances or taking out new loans, will affect their scores.The purpose of our analysis is to propose a model to predict consumer default that uses the same data as conventional credit scoring models, improves on their performance, benefiting both lenders and borrowers, and provides more transparency and accountability. To do so, we resort to deep learning, a type of machine l...

Financial Presentation of Alzheimer Disease and Related Dementias

“…Payment delinquency triggers penalty interest and fees, which we estimate would cost households in our sample $383 to $670 in the 4 years prior to dementia diagnosis alone. Credit for subprime borrowers is more difficult and costly to access; compared with those with prime scores, subprime borrowers pay an estimated $1085 to $1426 more in credit card interest annually due to higher rates . Credit data do not include utility payments, where nonpayment could result in a loss of service.…”

“…Credit for subprime borrowers is more difficult and costly to access; compared with those with prime scores, subprime borrowers pay an estimated $1085 to $1426 more in credit card interest annually due to higher rates. 33 Credit data do not include utility payments, where nonpayment could result in a loss of service. The extended period between financial indicators of ADRD and its diagnosis raises concerns about catastrophic financial events resulting from preclinical or undiagnosed ADRD for older adults.…”

Machine Learning–Based Interpretation and Visualization of Nonlinear Interactions in Prostate Cancer Survival

“…10 SHAP values have been applied in other fields outside of oncology, including in other fields of medicine such as anesthesia. [11][12][13][14] However, to our knowledge, the SHAP value framework for interpreting predictions has not been applied previously to clinical oncology. In this article, we describe a novel application of SHAP values to the prediction of overall survival (OS) in patients with prostate cancer, with an emphasis on applying the SHAP framework to visualize nonlinear relationships in a clinically intuitive…”

When the Lender Extends a Helping Hand: Native CDFI Client Counseling and Loan Performance in Indian Country

“…More broadly, our research contributes to the empirical literature on the importance of financial education for economic and credit outcomes (Miller et al, 2015;Hastings et al, 2013;Lusardi and Mitchell, 2014). Our results suggest that activities undertaken by lenders themselves to aid and support, as opposed to screen and supervise, clients may be an important determinant of loan outcomes-a possibility largely overlooked by existing empirical studies on loan repayment (Albanesi and Vamossy, 2019;Barbaglia et al, 2021;Butaru et al, 2016;Ciampi et al, 2021).…”