Coursera Plus Annual is 50% Off — Ends June 17.

Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CodeSignal

Recommendation Systems Quality Evaluation

via CodeSignal

Go to class Write review

Overview

This course focuses on metrics specific to recommendation systems, crucial for evaluating and optimizing model performance. You'll delve into recommendation-specific metrics such as Coverage, Serendipity, Novelty, and Diversity. Each metric is presented with theoretical insights and practical coding examples to illustrate their application.

Syllabus

  • Unit 1: Coverage in Recommendation Systems
    • Increase Recommendation Coverage
    • Implementing the Coverage Metric for Recommendation Systems
    • Calculating and Displaying Model Coverage
    • Calculating Recommendation Coverage in a Model-Based System
  • Unit 2: Understanding Novelty Metrics
    • Increase Novelty by Recommending Less Popular Items
    • Calculate Novelty Scores for Multiple Users' Recommendations
    • Calculate Average Novelty Across Multiple Users
    • Calculating Item Popularity and Novelty Score from Recommendations
  • Unit 3: Diversity in Recommendation Systems
    • Pairwise Cosine Similarity Matrix for Recommended Items
    • Sum of Pairwise Cosine Similarities for Recommended Items
    • Implementing a Diversity Metric for Recommendation Systems
    • Decrease Diversity by Making Item Vectors More Similar
    • Increase Diversity in Item Recommendations
  • Unit 4: Serendipity in Recommendation Systems
    • Boosting Serendipity in Recommendations
    • Calculating the Serendipity Score in a Recommendation System
    • Serendipity Calculation for Multiple Users

Reviews

Start your review of Recommendation Systems Quality Evaluation

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.