Using Stockranker Score Thresholds Instead of Daily Stock Rankings

Summary

The document contrasts selecting stocks by relative rank with selecting them by an absolute model score. A ranking method can always choose the highest-ranked names in a universe, even when their scores are weak. The proposed alternative sets a minimum score for entry and a lower score threshold for exiting holdings, so portfolio decisions depend on the model’s score level rather than its daily ordering alone.

Examples compare selecting and rotating a fixed number of top-ranked stocks with buying above a score of 0.9 and selling below 0.7; another variant lowers the exit threshold to 0.6. These examples illustrate the rule design, but the document provides no return statistics or controlled comparison. It cautions that results may be sensitive to threshold choice and suggests evaluating over longer backtest periods to reduce the chance of overfitting. The method also assumes that the model score meaningfully represents investment value, an assumption that requires validation.

Key ideas

• Relative ranking can select stocks even when every candidate has a weak model score.
• A score-threshold method buys when a stock exceeds an entry level and sells when a holding falls below an exit level.
• The examples use different entry and exit thresholds to illustrate how the rule can be adjusted.
• The author warns that score thresholds are sensitive and may be overfit.
• Longer backtests are suggested, though no performance results are reported.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.