PREVIEW: Screenshots of upcoming AI Factors

Thanks for paper. They are using classifiers algorithms (ex. RandomForestClassifier) with total return targets:

12-month return Target variable Target Variable
π‘Ÿπ‘’π‘‘π‘’π‘Ÿπ‘› β‰₯ 0.15 4
0.05 ≀ π‘Ÿπ‘’π‘‘π‘’π‘Ÿπ‘› < 0.15 3
0 ≀ π‘Ÿπ‘’π‘‘π‘’π‘Ÿπ‘› < 0.05 2
βˆ’0.15 ≀ π‘Ÿπ‘’π‘‘π‘’π‘Ÿπ‘› < 0 1
π‘Ÿπ‘’π‘‘π‘’π‘Ÿπ‘› < βˆ’0.15 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?