Effective Amazon Machine Learning

Preprocessing recapitulation

The following table recapitulates the different issues that one can find in raw data and whether Amazon ML offers ways to deal with them:

Linear model sensitivity	Available on Amazon ML
Missing values	Yes	Dealt with automatically
Standardization	Yes	z-score standardization
Outliers	Yes	Quantile binning
Multicollinearity	Yes	No
Imbalanced datasets	Yes	Uses the right metric F1 Score No sampling strategy (may exist in background)
Non linearities	Yes	Quantile binning