Building and Backtesting a StockRanker Machine Learning Strategy

Summary

This assignment outlines a workflow for creating a visual machine learning stock strategy using BigQuant’s StockRanker course and strategy template. The participant is asked to modify the model’s input features by adding personal factors, then backtest the resulting strategy over a period longer than one year. The completed strategy is to be shared for submission.

The document describes an exercise, not a full modeling recipe: it does not specify which features to use, how StockRanker is trained, how to prevent data leakage, or how to evaluate robustness. It mentions a Sharpe-based competition with rewards for the top submissions, but reports no strategy results or comparative evidence. A long backtest is part of the task, though its length alone cannot show that a model will perform reliably out of sample.

Key ideas

• The exercise uses a visual strategy template built around StockRanker.
• Participants are instructed to change the input features and add their own factors.
• The strategy must be backtested over more than one year and shared for submission.
• The assignment gives no guidance on feature validation or out-of-sample testing.

Tags

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