N°23-114: A Comprehensive Machine Learning Framework for Dynamic Portfolio Choice With Transaction Costs

We introduce a comprehensive computational framework for solving dynamic portfolio choice problems with many risky assets, transaction costs, and borrowing and short-selling constraints. Our approach leverages the synergy between Gaussian process regression and Bayesian active learning to efficiently approximate value and policy functions with a novel, formal way of characterizing the irregularly-shaped no-trade region; we then embed this into a discrete-time dynamic programming algorithm. This combination allows us to study dynamic portfolio choice problems with more risky assets than was previously possible. Our results indicate that giving the agent access to more assets may alleviate some illiquidity resulting from the presence of transaction costs.