Multilayer Perceptron Neural Network Models in Asset Pricing: An Empirical Study on Large-Cap US Stocks

TL;DR

This paper evaluates multilayer perceptron models for asset pricing of large-cap US stocks, highlighting their flexibility and risk management benefits, especially during different market periods including COVID-19.

Contribution

It introduces a dynamic-structured MLP model for factor-based asset pricing and assesses its performance and investment implications during varying market conditions.

Findings

MLP models with 2-3 hidden layers offer higher flexibility.

Models perform better in downside risk control than in maximizing returns.

Market conditions like COVID-19 impact model performance and investment strategies.

Abstract

In this study, MLP models with dynamic structure are applied to factor models for asset pricing tasks. Concretely, the MLP pyramid model structure was employed on firm-characteristic-sorted portfolio factors for modelling the large-capital US stocks. It was further developed as a practicable factor investing strategy based on the predictions. The main findings in this chapter were evaluated from two angles: model performance and investing performance, which were compared from the periods with and without COVID-19. The empirical results indicated that with the restrictions of the data size, the MLP models no longer perform "deeper, better", while the proposed MLP models with two and three hidden layers have higher flexibility to model the factors in this case. This study also verified the idea of previous works that MLP models for factor investing have more meaning in the downside risk control than in pursuing the absolute annual returns.