AI engineering glossary · Evaluation metrics
What is kendall's tau?
Kendall's tau (also called Kendall rank correlation): A measure of how similar two rankings are, based on pairs: (concordant pairs - discordant pairs) / total pairs. A pair is concordant if both rankings put the two items in the same order. It ranges from -1 to +1 and is used to compare rankings, such as a model's ordering against ground truth.
Kendall's tau: an example
Comparing two orderings of 5 items gives 10 pairs; 8 agree and 2 disagree, so tau = (8 - 2) / 10 = 0.6.
Related terms
- Spearman's rank correlation
- Normalised discounted cumulative gain
- Mean average precision
- Correlation coefficient
More Evaluation metrics terms
- Kolmogorov-Smirnov statistic
- Krippendorff's alpha
- Likelihood ratio
- Log loss
- Macro averaging
- Matthews correlation coefficient
- MAUVE
- Max error
Where you learn it
Kendall's tau is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.