المدربA parametric portfolio policy writes the weights directly as a function of the names’ characteristics, around a benchmark, and chooses to maximise the investor’s average utility over the sample (Brandt, Santa-Clara and Valkanov, 2009); there is no forecast, and the characteristics’ covariances with returns enter only through the portfolio’s outcome.
| coefficients chosen by | net Sharpe | (s.d., 5 pairs) | gross Sharpe | turnover |
|---|---|---|---|---|
| least squares, all names (predict, then optimise) | 0.19 | 0.09 | 0.60 | 2.95 |
| least squares, tradeable names | 1.52 | 0.23 | 1.92 | 1.59 |
| decision-focused learning | 1.51 | 0.22 | 1.92 | 2.75 |
| parametric portfolio policy | 1.49 | 0.23 | 1.92 | 2.90 |
| true coefficients | 1.57 | 0.24 | 1.97 | 1.50 |
ml_e2e.results.