Feature engineering — transforming raw data into informative features — is often what separates good models from great ones.

Common Feature Engineering Techniques

• Normalization/Scaling: Rescale features to similar ranges (essential for distance-based algorithms)
• One-hot encoding: Convert categorical variables to binary columns
• Log transform: Handle skewed distributions
• Interaction features: Multiply features to capture relationships
• Date features: Extract day of week, month, quarter from timestamps

The 80/20 Rule of ML

In practice, 80% of a data scientist's time goes to data cleaning and feature engineering — not model selection.

Reference:

Feature engineering guide

https://developers.google.com/machine-learning/data-prep/transform/normalization