Regimes Matter: Regime-Based Dynamic Asset Allocation Using Neural Networks

Abstract

We study Merton's optimal portfolio problem in a market responsive to macroeconomic regimes, as characterized by VIX. Instead of solving the traditional Hamilton-Jacobi-Bellman equation, we train an artificial neural network (ANN) to learn the optimal allocation as a feedback function. Our regime-specific strategy using a simple ANN with one hidden layer, benchmarked against the classical Merton portfolio, shows superior performance subject to realistic diversification constraints with borrowing/short selling excluded. A 35-year backtest (1990-2024), including 17 out-of-sample years, on a diversified portfolio of twelve assets plus cash, reveals that accounting for regime shifts improves both expected utility and average returns.