Your build starts here
Replace bracketed details with your own goal, context, and checks. Keep the first build small enough to inspect.
Create a baseline for predicting [target] at [prediction moment] from [available inputs]. Identify fields that would not exist at that moment and exclude leaked answers. Choose a split that respects [time, customer, session, or other grouping]. Fit preprocessing using training data only. Compare a simple rule with one reasonable model on the same held-out examples. Report the metric definition, baseline result, model result, and meaningful failure groups. Preserve reproducible split logic and avoid tuning against the final test set.Make this prompt yours
Replace bracketed fields with your goal, current behavior, and relevant evidence. Keep requirements that affect the task. Check the result against the acceptance criteria you supplied.
The docs behind it
These references explain the underlying concepts and APIs. The prompt templates and project plans are original examples to adapt to your own setup.
- scikit-learn — Dummy classifier baselines
- scikit-learn — Data leakage and preprocessing pitfalls
- scikit-learn — Training, validation, and cross-validation
Documentation links checked .
Editorial review · October 28, 2026
Limited: Original instructional template; not executed. Leakage-aware prompt asks for a group/time-appropriate split and reproducible held-out comparison; no model was trained.