Thanks for paper. They are using classifiers algorithms (ex. RandomForestClassifier) with total return targets:
| 12-month return Target variable | Target Variable |
|---|---|
| πππ‘π’ππ β₯ 0.15 | 4 |
| 0.05 β€ πππ‘π’ππ < 0.15 | 3 |
| 0 β€ πππ‘π’ππ < 0.05 | 2 |
| β0.15 β€ πππ‘π’ππ < 0 | 1 |
| πππ‘π’ππ < β0.15 | 0 |
It's strange that they used total return. I tried using a total return target (although with a regressor since we have not added classifier at the moment) also with SP500 universe, and it completely destroys the High - Low bucket performance. The High bucket I guess still shows some performance, but I would not use total return targets.
Intuitively only relative performance targets make sense, whether you use classifiers or regressors. Thoughts?