Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Alaya, Mohamed Ben, Kebaier, Ahmed, Sarr, Djibril
Format: Preprint
Veröffentlicht: 2021
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2110.15133
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914960308699136
author Alaya, Mohamed Ben
Kebaier, Ahmed
Sarr, Djibril
author_facet Alaya, Mohamed Ben
Kebaier, Ahmed
Sarr, Djibril
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2110_15133
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Deep Calibration of Interest Rates Model
Alaya, Mohamed Ben
Kebaier, Ahmed
Sarr, Djibril
Statistical Finance
Machine Learning
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.
title Deep Calibration of Interest Rates Model
topic Statistical Finance
Machine Learning
url https://arxiv.org/abs/2110.15133