Multiple Yield Curve Modeling and Forecasting using Deep Learning

TL;DR

This paper presents a deep learning approach that models multiple yield curves simultaneously, capturing their dependence structure to improve forecast accuracy and generate reliable point and interval predictions.

Contribution

It introduces a novel deep learning architecture combining self-attention and nonparametric quantile regression for yield curve modeling and forecasting.

Findings

Effective in capturing dependence among yield curves

Produces accurate point and interval forecasts

Avoids quantile crossing issues

Abstract

This manuscript introduces 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.