“Feature engineering is the process of transforming raw data into features that better represent the underlying problem to the predictive models, resulting in improved model accuracy on unseen data. You can see the dependencies in this definition:
• The performance measures you’ve chosen (RMSE? AUC?)
• The framing of the problem (classification? regression?)
• The predictive models you’re using (SVM?)
• The raw data you have selected and prepared (samples? formatting? cleaning?)”
Tomasz Malisiewicz