Modeling Impression Discounting in Large-scale Recommender Systems

ACM 2014 International Conference on Knowledge Discovery and Data Mining (SIGKDD 2014)


Recommender systems have become very important for many online activities, such as watching movies, shopping for products, and connecting with friends on social networks. User behavioral analysis and user feedback (both explicit and implicit) modeling are crucial for the improvement of any online recommender system. Widely adopted recommender systems at LinkedIn such as “People You May Know” and “Endorsements” are evolving by analyzing user behaviors on impressed recommendation items.

In this paper, we address modeling impression discounting of recommended items, that is, how to model user’s no-action feedback on impressed recommended items. The main contributions of this paper include (1) large-scale analysis of impression data from LinkedIn and KDD Cup; (2) novel anti-noise regression techniques, and its application to learn four different impression discounting functions including linear decay, inverse decay, exponential decay, and quadratic decay; (3) applying these impression discounting functions to LinkedIn’s “People You May Know” and “Endorsements” recommender systems.


[ Paper in PDF ] [ Poster in PDF ] [ Presentation in PDF ]


 author = {Lee, Pei and Lakshmanan, Laks V.S. and Tiwari, Mitul and Shah, Sam},
 title = {Modeling Impression Discounting in Large-scale Recommender Systems},
 booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
 series = {KDD '14},
 year = {2014},
 isbn = {978-1-4503-2956-9},
 location = {New York, New York, USA},
 pages = {1837--1846},
 numpages = {10},
 url = {},
 doi = {10.1145/2623330.2623356},
 acmid = {2623356},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {impression discounting, recommender system},