LIFE STYLE

Recommender Systems: Evaluation and Metrics

Evaluate recommender systems, with several families of metrics, including ones to measure prediction accuracy, rank accuracy, decision-support, and other factors such as diversity, product coverage, and serendipity. How different metrics relate to different user goals and business goals. How to rigorously conduct offline evaluations (i.e., how to prepare and sample data, and how to aggregate results). Online (experimental) evaluation. Have the tools to compare different recommender system alternatives for a wide variety of uses.

Basic Prediction and Recommendation Metrics
Advanced Metrics and Offline Evaluation
Online Evaluation
Evaluation Design