Evaluating Credit VIX (CDS IV) Prediction Methods with Incremental Batch Learning

TL;DR

This study compares SVM, Gradient Boosting, and Attention-GRU models in predicting credit default swap implied volatility using incremental learning, aiming to identify effective methods for financial risk forecasting.

Contribution

It introduces a comparative evaluation of multiple machine learning models with incremental learning for CDS implied volatility prediction.

Findings

Gradient Boosting outperforms other models in accuracy

Attention-GRU shows strong temporal pattern recognition

Classical ML methods remain competitive with SOTA techniques

Abstract

This paper presents the experimental process and results of SVM, Gradient Boosting, and an Attention-GRU Hybrid model in predicting the Implied Volatility of rolled-over five-year spread contracts of credit default swaps (CDS) on European corporate debt during the quarter following mid-May '24, as represented by the iTraxx/Cboe Europe Main 1-Month Volatility Index (BP Volatility). The analysis employs a feature matrix inspired by Merton's determinants of default probability. Our comparative assessment aims to identify strengths in SOTA and classical machine learning methods for financial risk prediction