DMCA
Naïve filterbots for robust cold-start recommendations (2006)
| Venue: | Proc. of the 12th ACM SIGKDD Int’l Conf |
| Citations: | 30 - 3 self |
BibTeX
@INPROCEEDINGS{Park06naïvefilterbots,
author = {Seung-taek Park and David Pennock and Omid Madani and Nathan Good and Dennis Decoste},
title = {Naïve filterbots for robust cold-start recommendations},
booktitle = {Proc. of the 12th ACM SIGKDD Int’l Conf},
year = {2006},
pages = {699--705}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The goal of a recommender system is to suggest items of interest to a user based on historical behavior of a community of users. Given detailed enough history, item-based collaborative filtering (CF) often performs as well or better than almost any other recommendation method. However, in cold-start situations—where a user, an item, or the entire system is new—simple non-personalized recommendations often fare better. We improve the scalability and performance of a previous approach to handling cold-start situations that uses filterbots, or surrogate users that rate items based only on user or item attributes. We show that introducing a very small number of simple filterbots helps make CF algorithms more robust. In particular, adding just seven global filterbots improves both user-based and item-based CF in cold-start user, cold-start item, and cold-start system settings. Performance is better when data is scarce, performance is no worse when data is plentiful, and algorithm efficiency is negligibly affected. We systematically compare a non-personalized baseline, user-based CF, item-based CF, and our bot-augmented user- and item-based CF algorithms using three data sets (Yahoo! Movies, MovieLens, and Each-Movie) with the normalized MAE metric in three types of cold-start situations. The advantage of our “naïve filterbot” approach is most pronounced for the Yahoo! data, the sparsest of the three data sets.
Keyphrases
robust cold-start recommendation na ve filterbots cold-start situation item-based cf data set enough history surrogate user item-based cf algorithm bot-augmented user recommender system item-based collaborative filtering yahoo data cold-start user non-personalized baseline yahoo movie user-based cf recommendation method new simple non-personalized recommendation item attribute simple filterbots help historical behavior small number algorithm efficiency cold-start system setting cold-start item normalized mae entire system na ve filterbot approach rate item previous approach
