P62Feature EngineeringIntermediateChoose12 min
Choose an Encoding Strategy for a High-Cardinality Category
Choose encoding for a category with many values.
#choose#encoding#high-cardinality
Scenario
merchant_id has 18,000 values and new merchants each week.
Problem statement
Recommend an encoding with trade-offs.
Your Task
- Address cardinality.
- Handle unseen values.
- Address leakage.
Related Concepts
One-hotTarget encoding
Ready to count this problem?
Mark it complete when you have reasoned through the solution in your own words.