Note
Garbage in garbae out. It is the features that
What is involved:
Want to assess the usefulness of chosen features
Measuring feature importance:
Quantifying the contribution of each feature to the model’s predictions. This can be done through various methods like statistical tests, model-specific importance scores, or permutation importance.
Analysing feature relationships:
Investigating correlations and redundancy,
Assessing feature impact on model performance:
Example:
When are we done:
- **Reaching a stable and satisfactory model performance
- **No further room for improvement
- **Understanding the model’s decision-making process