Ranking on English AI Terms Dictionary

Learning to rank

Sat, 18 Jul 2026 10:04:43 +0000

Definition

Unlike standard classification or regression, learning to rank focuses on predicting a relative ordering of items. It uses pairwise, listwise, or pointwise approaches to minimize ranking errors like NDCG or MAP. This technique is essential for information retrieval systems, recommendation engines, and ad placement, where the goal is to present the most relevant results at the top of a list rather than just predicting individual labels.

Summary

Learning to rank is a supervised machine learning technique used to order items by their relevance to a given query, commonly used in search engines.

Bradley–Terry model

Sat, 18 Jul 2026 09:48:33 +0000

Definition

The Bradley-Terry model is a probabilistic model widely used in psychometrics and machine learning to handle pairwise comparisons. It assigns a latent score to each item, calculating the probability that item i is chosen over item j based on their relative scores. This model is fundamental in ranking systems, such as chess Elo ratings, A/B testing analysis, and preference learning in reinforcement learning from human feedback (RLHF).

Summary

A statistical model used to analyze paired comparison data, estimating the probability that one item is preferred over another.