This thesis investigates the application of Kolmogorov-Arnold Networks (KANs) to financial forecasting, with a specific focus on predicting the S&P 500 index—comprising the 500 largest US companies—and the VIX, a primary measure of market volatility. The performance of KANs is evaluated against standard benchmarks, including forward filling, ARIMA, MLP, and LSTM models, using datasets that vary in length and input features.

This thesis investigates the application of Kolmogorov-Arnold Networks (KANs) to financial forecasting, with a specific focus on predicting the S&P 500 index—comprising the 500 largest US companies—and the VIX, a primary measure of market volatility. The performance of KANs is evaluated against standard benchmarks, including forward filling, ARIMA, MLP, and LSTM models, using datasets that vary in length and input features.

Kolmogorov–Arnold Networks for Financial Forecasting: The case of VIX and S&P 500

ZANATTA, SARA
2024/2025

Abstract

This thesis investigates the application of Kolmogorov-Arnold Networks (KANs) to financial forecasting, with a specific focus on predicting the S&P 500 index—comprising the 500 largest US companies—and the VIX, a primary measure of market volatility. The performance of KANs is evaluated against standard benchmarks, including forward filling, ARIMA, MLP, and LSTM models, using datasets that vary in length and input features.
2024
Kolmogorov–Arnold Networks for Financial Forecasting: The case of VIX and S&P 500
This thesis investigates the application of Kolmogorov-Arnold Networks (KANs) to financial forecasting, with a specific focus on predicting the S&P 500 index—comprising the 500 largest US companies—and the VIX, a primary measure of market volatility. The performance of KANs is evaluated against standard benchmarks, including forward filling, ARIMA, MLP, and LSTM models, using datasets that vary in length and input features.
KANs
Forecasting
VIX
Lauree magistrali
File in questo prodotto:
File Dimensione Formato  
Zanatta_Sara.pdf

accesso aperto

Dimensione 1.46 MB
Formato Adobe PDF
Visualizza/Apri
1.46 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/101987