A1372
Title: Moving forward from predictive regressions: Boosting asset allocation decisions
Authors: Henri Nyberg - University of Turku (Finland) [presenting]
Lauri Nevasalmi - University of Turku (Finland)
Abstract: A flexible utility-based empirical approach is introduced to determine asset allocation decisions between risky and risk-free assets directly. This is in contrast to the commonly used two-step approach where least squares optimal statistical equity premium predictions are first constructed to form portfolio weights before economic criteria are used to evaluate resulting portfolio performance. Our single-step customized gradient boosting method is specifically designed to find optimal portfolio weights in a direct utility maximization. Empirical results of the monthly U.S. data show the superiority of boosted portfolio weights over several benchmarks, generating interpretable results and profitable asset allocation decisions.