Earlier we had a weighted ensemble model that essentially took the r-squared values of Annual and Quarterly and used that as a weighting factor to ensemble them.
It was here, that realized we were not calculating or saving the predicted fwd return - we were only calculating scores, writing them to a scoring summary and saving the R-squared.
So I changed things around. I added a stacked meta ensemble, and will describe how these work below. We now run BOTH of these.
Weighted Ensemble
- A simple blend of the two base models.
- Annual and quarterly predictions are combined with weights proportional to their out-of-sample R² performance.
Result: ensemble_pred_fwdreturn and ensemble_pred_fwdreturn_pct.
This improves stability but is still fairly “rigid.”
Meta-Model Ensemble (Stacked Ensemble)
A second-level model (XGBoost) is trained on:
- Predictions from the annual model
- Predictions from the quarterly model
- Additional features (sector, industry, etc.)
This meta-model learns the optimal way to combine signals dynamically rather than relying on fixed weights.
Result: ensemble_pred_fwdreturn_meta and ensemble_pred_fwdreturn_meta_pct.
How well did it work?
Results
- Weighted Ensemble: R² ~0.19, Spearman ~0.50
- Meta-Model Ensemble: R² ~0.75, Spearman ~0.65
Quintile backtests confirm a strong monotonic relationship between predicted quintiles and realized forward returns.
