Feature Engineering

Thomas Bayes


In Feature engineering, you are:

  • creating derived features
  • normalize them


Fraud detection

Data Mining - Fraud Detection

  • Aggregated variables. Example: aggregated transaction count per account in last 24 hours to spot abnormal amount
  • Mismatch variables. Example: delivery country <> normal delivery country
  • Risk tables. Probability Risks grouped by country, state, IP Address, etc..

Documentation / Reference

Discover More
P Value Pipeline
Data Mining - (Life cycle|Project|Data Pipeline)

Data mining is an experimental science. Data mining reveals correlation, not causation. With good data, you will make good algorithm. The most preferable solution is then to work on good features....

Share this page:
Follow us:
Task Runner