Online Learning of Portfolio Ensembles with Sector Exposure Regularization
This work addresses risk management in financial portfolio optimization for investors, though it appears incremental as it builds on existing mean-reversion algorithms with a new regularization approach.
The paper tackled the problem of online learning for portfolio ensembles by introducing sector exposure regularization to encourage diversification and reduce risk, achieving a logarithmic regret bound and a significant increase in risk-adjusted return (Sharpe ratio) in empirical tests.
We consider online learning of ensembles of portfolio selection algorithms and aim to regularize risk by encouraging diversification with respect to a predefined risk-driven grouping of stocks. Our procedure uses online convex optimization to control capital allocation to underlying investment algorithms while encouraging non-sparsity over the given grouping. We prove a logarithmic regret for this procedure with respect to the best-in-hindsight ensemble. We applied the procedure with known mean-reversion portfolio selection algorithms using the standard GICS industry sector grouping. Empirical Experimental results showed an impressive percentage increase of risk-adjusted return (Sharpe ratio).