Forecasting VIX using interpretable Kolmogorov-Arnold networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cho, So-Yoon, Lee, Sungchul, Kim, Hyun-Gyoon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910810405601280
author Cho, So-Yoon
Lee, Sungchul
Kim, Hyun-Gyoon
author_facet Cho, So-Yoon
Lee, Sungchul
Kim, Hyun-Gyoon
contents This paper presents the use of Kolmogorov-Arnold Networks (KANs) for forecasting the CBOE Volatility Index (VIX). Unlike traditional MLP-based neural networks that are often criticized for their black-box nature, KAN offers an interpretable approach via learnable spline-based activation functions and symbolification. Based on a parsimonious architecture with symbolic functions, KAN expresses a forecast of the VIX as a closed-form in terms of explanatory variables, and provide interpretable insights into key characteristics of the VIX, including mean reversion and the leverage effect. Through in-depth empirical analysis across multiple datasets and periods, we show that KANs achieve competitive forecasting performance while requiring significantly fewer parameters compared to MLP-based neural network models. Our findings demonstrate the capacity and potential of KAN as an interpretable financial time-series forecasting method.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00980
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Forecasting VIX using interpretable Kolmogorov-Arnold networks
Cho, So-Yoon
Lee, Sungchul
Kim, Hyun-Gyoon
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
This paper presents the use of Kolmogorov-Arnold Networks (KANs) for forecasting the CBOE Volatility Index (VIX). Unlike traditional MLP-based neural networks that are often criticized for their black-box nature, KAN offers an interpretable approach via learnable spline-based activation functions and symbolification. Based on a parsimonious architecture with symbolic functions, KAN expresses a forecast of the VIX as a closed-form in terms of explanatory variables, and provide interpretable insights into key characteristics of the VIX, including mean reversion and the leverage effect. Through in-depth empirical analysis across multiple datasets and periods, we show that KANs achieve competitive forecasting performance while requiring significantly fewer parameters compared to MLP-based neural network models. Our findings demonstrate the capacity and potential of KAN as an interpretable financial time-series forecasting method.
title Forecasting VIX using interpretable Kolmogorov-Arnold networks
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2502.00980