.png){kind=icon}
.png){kind=icon}
Return
Combining deep learning with econometric models: volatility forecasting using the KAN-GARCH-MIDAS framework
.png){kind=icon}
PRE
AI
DOI：10.1080/15140326.2025.2555479.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Machine learning and deep learning are increasingly applied in finance, yet few studies explore how they can enhance traditional econometric models. This study proposes an innovative KAN-GM model, integrating the Kolmogorov-Arnold network (KAN) with the GARCH-MIDAS model to extract nonlinear macroeconomic features for volatility forecasting. Empirical results show that KAN-GM outperforms traditional GARCH in MAE and MedAE, consistently ranks in the optimal model set via MCS tests, and demonstrates strong cross-market adaptability (stocks and forex). It also maintains robustness pre- and post-COVID-19. The model effectively combines deep learning and econometrics, improving financial risk prediction.
Keywords:
Forecasting
volatility
GARCH-MIDAS
KAN
Journal
J
IF:
2
Papers:
73
Citations:
0