AutoTrain MLBefore you begin: use a dataset you are allowed to process, keep a holdout that reflects the real prediction setting, and write down the decision the model is intended to support.
1. Choose a numeric target
Confirm that the target is numeric and available at the intended prediction time.
Verify before continuingThe target, row meaning, and prediction timing are explicit.
2. Split and transform
Create the validation split before fitting imputers, encoders, or scalers. This prevents information from the holdout data leaking into training.
Verify before continuingTransformations are learned from training rows only and can be reproduced during testing.
3. Compare metrics
Use MAE for an interpretable average error, RMSE when large errors deserve more weight, and R² to describe explained variance.
Verify before continuingThe selected metric reflects the cost of errors and is compared on the same holdout.
4. Inspect residuals
Look for systematic error by target range, time, geography, or customer group before deployment.
Verify before continuingRepresentative new inputs produce valid outputs and failures are handled clearly.
Final checklist
- Dataset version and intended use are documented.
- Preprocessing and validation settings match the saved experiment.
- Metrics are interpreted with class balance, error cost, and limitations in mind.
- New-data testing succeeds with the exact production schema.
- A fallback and monitoring plan exist before deployment.
Next step
Open the dashboard to apply this guide to a saved dataset and experiment.
Open dashboard