Application of Deep Learning for Factor Timing in Asset Management
This addresses factor timing challenges for asset managers, but it is incremental as it applies existing models to a specific financial factor.
The paper applied regression models including OLS, Ridge, Random Forest, and Fully-connected Neural Network to predict the CMA factor premium for factor timing in asset management, finding that more flexible models like neural networks achieved higher out-of-sample R-squared and better backtesting performance but suffered from unstable optimal weights leading to high transaction costs, which could be mitigated by reducing rebalance frequency.
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.