Turning raw data into inputs a model can use better.
Feature engineering is taco night prep. Chop the toppings and label the lava salsa before Uncle Dave grabs it.
You meet it in spreadsheet data. For old-school models, it can make or break risk checks and recommendations.
Representation Learning
Representation Learning lets the model learn features itself, so people hand-build fewer.
Supervised Learning
Feature engineering often prepares the input before Supervised Learning trains.
Deep Learning
Deep Learning made many hand-built features less important.