- Level Foundation
- المدة 7 ساعات hours
- الطبع بواسطة University of Minnesota
-
Offered by
عن
In this course you will learn how to evaluate recommender systems. You will gain familiarity 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. You will learn how different metrics relate to different user goals and business goals. You will also learn how to rigorously conduct offline evaluations (i.e., how to prepare and sample data, and how to aggregate results). And you will learn about online (experimental) evaluation. At the completion of this course you will have the tools you need to compare different recommender system alternatives for a wide variety of uses.الوحدات
Preface
2
Videos
- Introduction to Evaluation and Metrics
- The Goals of Evaluation
Basic Prediction and Recommendation Metrics
1
Assignment
- Basic Prediction and Recommendation Metrics Assignment
5
Videos
- Hidden Data Evaluation
- Prediction Accuracy Metrics
- Decision Support Metrics
- Rank-Aware Top-N Metrics
- Assignment Intro Video
1
Readings
- Metric Computation Assignment Instructions
Advanced Metrics and Offline Evaluation
1
Assignment
- Offline Evaluation and Metrics Quiz
5
Videos
- Beyond Basic Evaluation
- Additional Item and List-Based Metrics
- Experimental Protocols
- Unary Data Evaluation
- Temporal Evaluation of Recommenders (Interview with Neal Lathia)
Honors
1
Assignment
- Programming Assignment Quiz
1
Videos
- Programming Assignment Introduction
1
Readings
- Evaluating Recommenders
Online Evaluation
1
Assignment
- Online Evaluation Quiz
4
Videos
- Introduction to Online Evaluation and User Studies
- Usage Logs and Analysis
- A/B Studies (Field Experiments)
- User-Centered Evaluation (Interview with Bart Knijnenburg)
Evaluation Design
1
Assignment
- Assignment: Evaluation Design Cases
3
Videos
- Matching Evaluation to the Problem/Challenge
- Case Examples
- Assignment Intro Video
2
Readings
- Intro to Assignment: Evaluation Design Cases
- Quiz Debrief
Auto Summary
Enhance your Data Science & AI skills with "Recommender Systems: Evaluation and Metrics" on Coursera. This foundational course, led by expert instructors, explores various metrics for evaluating recommender systems, including prediction accuracy, rank accuracy, and diversity. You'll learn to align metrics with user and business goals and conduct both offline and online evaluations. Ideal for beginners, the course spans 420 minutes and offers Starter and Professional subscription options.

Michael D. Ekstrand

Joseph A Konstan