Application of Deep Learning for Factor Timing in Asset Management

TL;DR

This paper evaluates various regression models, including neural networks, for predicting factor premiums and timing investments, finding flexible models perform better but face stability issues, which can be mitigated by adjusting rebalancing frequency.

Contribution

It compares the performance of linear and flexible models like neural networks in factor timing, highlighting stability challenges and proposing rebalancing adjustments to reduce costs.

Findings

Flexible models outperform linear models in explaining factor premium variance.

Neural networks provide better factor timing performance but have unstable optimal weights.

Reducing rebalancing frequency decreases transaction costs for flexible models.

Abstract

The paper examines the performance of regression models (OLS linear regression, Ridge regression, Random Forest, and Fully-connected Neural Network) on the prediction of CMA (Conservative Minus Aggressive) factor premium and the performance of factor timing investment with them. Out-of-sample R-squared shows that more flexible models have better performance in explaining the variance in factor premium of the unseen period, and the back testing affirms that the factor timing based on more flexible models tends to over perform the ones with linear models. However, for flexible models like neural networks, the optimal weights based on their prediction tend to be unstable, which can lead to high transaction costs and market impacts. We verify that tilting down the rebalance frequency according to the historical optimal rebalancing scheme can help reduce the transaction costs.