How can I detect data leakage?

Check whether each input value would have been available at the historical prediction time. Common leakage sources include future outcomes in feature columns, backdated events, and historical attributes overwritten with today’s values.

Unexpectedly strong evaluation results, a production performance drop, or one column dominating model explanations are reasons to investigate. None proves leakage on its own.

Use Training Diagnostics and Model Explainability to inspect suspicious results. Choose evaluation splits that reflect how the model will be used.