General Goals of Evaluation Design: Accuracy, Coverage,
Confidence and Trust, Novelty, Serendipity, Diversity, Scalability,
Segmenting the Ratings for Training and Testing,
Accuracy Metrics in Offline Evaluation.
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Recommendation systems subject unit-5
Typology: Slides
2025/2026
1 / 23
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Recommendation systems and more Slides Computer science in PDF only on Docsity!
General Goals of Evaluation Design: Accuracy, Coverage,
Confidence and Trust, Novelty, Serendipity, Diversity, Scalability,
Segmenting the Ratings for Training and Testing,
Accuracy Metrics in Offline Evaluation.
Scalability
Measuring the Accuracy of Ratings Prediction
- (^) Many recommender systems predict numerical ratings (e.g., Netflix ratings from 1- stars).
- (^) The quality of these predictions is assessed using metrics like RMSE and MAE. RMSE versus MAE
Evaluating Ranking via Correlation
- (^) Instead of just predicting ratings, recommendation systems should rank items in the correct order.
- (^) Ranking correlation measures how similar the predicted ranking is to the actual user preferences.