New Risk Management Study Findings Recently Were Reported by Researchers at University of Nottingham (Discrete-Time Survival Models with Neural Networks for Age-Period-Cohort Analysis of Credit Risk): Insurance – Risk Management

2024 MAR 12 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- Investigators publish new report on risk management. According to news originating from Ningbo, People’s Republic of China, by NewsRx editors, the research stated, “Survival models have become popular for credit risk estimation. Most current credit risk survival models use an underlying linear model.”

Financial supporters for this research include Ningbo Municipal Government; Microsoft Research Scholarship.

Our news journalists obtained a quote from the research from University of Nottingham: “This is beneficial in terms of interpretability but is restrictive for real-life applications since it cannot discover hidden nonlinearities and interactions within the data. This study uses discrete-time survival models with embedded neural networks as estimators of time to default. This provides flexibility to express nonlinearities and interactions between variables and hence allows for models with better overall model fit. Additionally, the neural networks are used to estimate age-period-cohort (APC) models so that default risk can be decomposed into time components for loan age (maturity), origination (vintage), and environment (e.g., economic, operational, and social effects). These can be built as general models or as local APC models for specific customer segments. The local APC models reveal special conditions for different customer groups. The corresponding APC identification problem is solved by a combination of regularization and fitting the decomposed environment time risk component to macroeconomic data since the environmental risk is expected to have a strong relationship with macroeconomic conditions.”

According to the news reporters, the research concluded: “Our approach is shown to be effective when tested on a large publicly available US mortgage dataset. This novel framework can be adapted by practitioners in the financial industry to improve modeling, estimation, and assessment of credit risk.”

For more information on this research see: Discrete-Time Survival Models with Neural Networks for Age-Period-Cohort Analysis of Credit Risk. Risks, 2024,12(2):31. (Risks - http://www.mdpi.com/journal/risks). The publisher for Risks is MDPI AG.

A free version of this journal article is available at https://doi.org/10.3390/risks12020031.

Our news editors report that additional information may be obtained by contacting Hao Wang, School of Computer Science, University of Nottingham, Ningbo 315100, People’s Republic of China. Additional authors for this research include Anthony Bellotti, Rong Qu, Ruibin Bai.

(Our reports deliver fact-based news of research and discoveries from around the world.)