Asset Allocation: A Statistical Learning Approach

This proposal focuses on developing a statistical learning approach to the asset allocation problem. The problem is to optimally allocate available funds among a given collection assets. It is of fundamental importance to financial management and is faced daily by financial institutions, asset managers, pension plans, university endowments, insurance companies, as well as individual investors. Pioneering works of Markowitz on mean-variance portfolio optimization laid the theoretical foundations of applying optimization to the asset allocation problem. Notwithstanding the enormous importance and influence of these classical contributions, the fact remains that, from the applied point of view, Markowitz-style portfolio policies are often outperformed by the naive 1/N equal weights portfolio policy out of sample due to the difficulties in estimating assets’ expected returns, volatilities and correlations from historical data. The goal of the project is to improve out of sample performance of asset allocation building on recent advances in statistical learning.