We propose that investment strategies should be evaluated based on their net-of-trading-cost return for each level of risk, which we term the “implementable efficient frontier.” While numerous studies use machine learning return forecasts to generate portfolios, their agnosticism toward trading costs leads to excessive reliance on fleeting small-scale characteristics, resulting in poor net returns. We develop a framework that produces a superior frontier by integrating trading-cost-aware portfolio optimization with machine learning. The superior net-of-cost performance is achieved by learning directly about portfolio weights using an economic objective. Further, our model gives rise to a new measure of “economic feature importance.”

We propose a statistical model of heterogeneous beliefs wherein investors are represented as different machine learning model specifications. Investors form return forecasts from their individual models using common data inputs. We measure disagreement as forecast dispersion across investor-models (MFD). Our measure aligns with analyst forecast disagreement but more powerfully predicts returns. We document a large and robust association between belief disagreement and future returns. A decile spread portfolio that sells stocks with high disagreement and buys stocks with low disagreement earns a value-weighted return of 13% per year. Further analyses suggest MFD-alpha is mispricing induced by short-sale costs and limits-to-arbitrage.