Deep Calibration of Interest Rates Model

TL;DR

This paper introduces a deep learning-based calibration method for interest rate models, outperforming traditional techniques and applicable to models like G2++ and CIR, using neural networks trained on financial data.

Contribution

It presents a novel deep learning calibration approach for interest rate models, demonstrating improved accuracy and systematic application to models like G2++ and CIR.

Findings

Deep learning calibration outperforms classic methods.

Covariances are more effective than correlations for training.

The approach is systematic and adaptable to different models.

Abstract

For any financial institution, it is essential to understand the behavior of interest rates. Despite the growing use of Deep Learning, for many reasons (expertise, ease of use, etc.), classic rate models such as CIR and the Gaussian family are still widely used. In this paper, we propose to calibrate the five parameters of the G2++ model using Neural Networks. Our first model is a Fully Connected Neural Network and is trained on covariances and correlations of Zero-Coupon and Forward rates. We show that covariances are more suited to the problem than correlations due to the effects of the unfeasible backpropagation phenomenon, which we analyze in this paper. The second model is a Convolutional Neural Network trained on Zero-Coupon rates with no further transformation. Our numerical tests show that our calibration based on deep learning outperforms the classic calibration method used as a benchmark. Additionally, our Deep Calibration approach is designed to be systematic. To illustrate this feature, we applied it to calibrate the popular CIR intensity model.