hmu.ai
Back to AI Dictionary
AI Dictionary

Feature Engineering

Definition

The process of using domain knowledge to extract features from raw data via data mining techniques.

Deep Dive

Feature Engineering is the art and science of transforming raw data into features that better represent the underlying problem to the predictive models, resulting in improved model accuracy and performance. This process involves leveraging domain knowledge to meticulously select, combine, and manipulate variables, making complex relationships more apparent to machine learning algorithms. It's a critical step that often has a greater impact on model effectiveness than choosing a different algorithm.

Examples & Use Cases

  • 1For predicting house prices, combining 'square footage' and 'number of rooms' into a 'price per square foot' feature
  • 2In customer churn prediction, calculating the 'average time since last purchase' from raw transaction logs
  • 3Extracting edge detectors or color histograms from raw image pixels for computer vision tasks

Related Terms

Data PreprocessingFeature SelectionDimensionality Reduction

Part of the hmu.ai extensive business and technology library.