Whitepapers

Using Statistical Distances for Machine Learning

Data problems in machine learning come in a wide variety, from sudden data pipeline failures to feature drift over time. Statistical distance measures give teams an indication of changes in the data affecting a model and insights for troubleshooting, helping teams get in front of problems before they impact business outcomes. 

In this white paper, you’ll learn: 

  • How and where to use common statistical distance checks in machine learning
  • Use cases for statistical distance checks across model inputs, model outputs and actuals.
  • When and how to use specific statistical distance measures — including population stability index (PSI), Kullback–Leibler divergence (KL-Divergence), Jensen–Shannon divergence (JS-Divergence) and Earth Mover’s Distance (EMD)
  • Type of bins and how to ensure statistical distance check metrics make sense in real-world applications

Download this guide on statistical distance checks now.

Read the whitepaper

Ready to level up your ML observability game?

Request A Demo