An Analysis of Probabilistic Methods for Top-N Recommendation in Collaborative Filtering thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

An Analysis of Probabilistic Methods for Top-N Recommendation in Collaborative Filtering

Published on Nov 30, 20113670 Views

In this work we perform an analysis of probabilistic approaches to recommendation upon a different validation perspective, which focuses on accuracy metrics such as recall and precision of the recomme

Related categories

Chapter list

An Analysis of Probabilistic Methods for Top-N Recommendation in Collaborative Filtering00:00
Outline00:17
Recommendation Problem00:43
Evaluating Recommendations01:39
Precision and Recall of the Recommendation List02:47
Evaluating User Satisfaction03:06
Prediction vs Recommendation Accuracy04:01
Performance of Recommender Algorithms on Top-N Recommendation Tasks04:43
Probabilistic Approaches to Recommendation: Advantages05:31
Probabilistic Approaches to Recommendation06:38
Probabilistic Modeling of Preference Data: An Overview07:48
Exploiting Probabilities for Item Ranking08:58
Experimental Evaluation09:38
Predicted Preference10:19
Predicted Preference: Discussion10:43
Item Selection and Relevance11:19
Conclusion11:54
Thanks13:06