KAN based Autoencoders for Factor Models

2024/08/04 by Wang, Tianqi, Singh, Shubham · 1 citation
#Artificial Intelligence (cs.AI) #Computational Finance (q-fin.CP) #FOS: Computer and information sciences #FOS: Economics and business #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2408.02694

Abstract

Inspired by recent advances in Kolmogorov-Arnold Networks (KANs), we introduce a novel approach to latent factor conditional asset pricing models. While previous machine learning applications in asset pricing have predominantly used Multilayer Perceptrons with ReLU activation functions to model latent factor exposures, our method introduces a KAN-based autoencoder which surpasses MLP models in both accuracy and interpretability. Our model offers enhanced flexibility in approximating exposures as nonlinear functions of asset characteristics, while simultaneously providing users with an intuitive framework for interpreting latent factors. Empirical backtesting demonstrates our model's superior ability to explain cross-sectional risk exposures. Moreover, long-short portfolios constructed using our model's predictions achieve higher Sharpe ratios, highlighting its practical value in investment management.

Cited by

• Nonlinear Factor Decomposition via Kolmogorov-Arnold Networks: A Spectral Approach to Asset Return Analysis

Related

• From Factor Models to Deep Learning: Machine Learning in Reshaping Empirical Asset Pricing
• Asset Pricing and Machine Learning: A critical review
• NeuralFactors: A Novel Factor Learning Approach to Generative Modeling of Equities
• Multilayer Perceptron Neural Network Models in Asset Pricing: An Empirical Study on Large-Cap US Stocks
• Deep Learning for Conditional Asset Pricing Models