K-Nearest Neighbors (page 6 of 6)

Positives of KNN:
1. Understandable and easy to explain to managers using this model
2. KNN may be used for regression and classification problems
Negatives of KNN:
1. Supports the status quo, not diversity (i.e., looking for similar neighbors)
2. May be computational intensive depending on the number of features (i.e., efficiency is inversely proportional to the number of features)
3. It is sensitive to outliers and missing data.



Sample Scenario: Predicting Customer Loyalty Categories