ASTIN: Multiple Yield Curve Modeling and Forecasting using Deep Learning

Multiple Yield Curve Modeling and Forecasting using Deep Learning

We introduce some deep learning models that simultaneously describe the dynamics of several yield curves. We aim to learn the dependence structure among the different yield curves induced by the globalization of financial markets and exploit it to produce more accurate forecasts. By combining the self-attention mechanism and nonparametric quantile regression, our model generates both point and interval forecasts of future yields. The architecture is designed to avoid quantile crossing issues affecting multiple quantile regression models. Numerical experiments conducted on two different datasets confirm the effectiveness of our approach. Finally, we explore potential extensions and enhancements by incorporating deep ensemble methods and transfer learning mechanisms.

Speaker:

Salvatore Scognamiglio is Assistant Professor in Actuarial Mathematics at the University of Naples Parthenope. He holds a PhD in Economics and Statistics (Actuarial Science) and has been a visiting researcher at Bayes Business School in London and RiskLab at ETH Zurich. His research focuses on applying machine learning and deep learning to risk management, insurance pricing, and mortality forecasting, as well as on efficient simulation methods and multivariate time series modeling. Salvatore has received multiple international awards, including some Best Paper Awards from the IAA’s Life and ASTIN Sections, the Bob Alting von Geusau Prize from the IAA's AFIR-ERM Section, and the Swiss Re Prize. He has led several funded research projects for the Society of Actuaries, the Casualty Actuarial Society, and the IAA Life Section. He has published extensively in leading journals, including ASTIN Bulletin, Insurance: Mathematics and Economics, Scandinavian Actuarial Journal, European Actuarial Journal and North American Actuarial Journal.