TY  - CONF
AU  - Schein, Andrew I.
AU  - Popescul, Alexandrin
AU  - Ungar, Lyle H.
AU  - Pennock, David M.
A2  - 
T1  - Methods and Metrics for Cold-start Recommendations
T2  - Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
PB  - ACM
CY  - New York, NY, USA
PY  - 2002/
M2  - 
VL  - 
IS  - 
SP  - 253
EP  - 260
UR  - http://doi.acm.org/10.1145/564376.564421
M3  - 10.1145/564376.564421
KW  - recommender
KW  - metrics
KW  - start
KW  - groc
KW  - cold
KW  - croc
L1  - 
SN  - 1-58113-561-0
N1  - Methods and metrics for cold-start recommendations
N1  - 
AB  - We have developed a method for recommending items that combines content and collaborative data under a single probabilistic framework. We benchmark our algorithm against a naïve Bayes classifier on the  cold-start problem, where we wish to recommend items that no one in the community has yet rated. We systematically explore three testing methodologies using a publicly available data set, and explain how these methods apply to specific real-world applications. We advocate heuristic recommenders when benchmarking to give competent baseline performance. We introduce a new performance metric, the CROC curve, and demonstrate empirically that the various components of our testing strategy combine to obtain deeper understanding of the performance characteristics of recommender systems. Though the emphasis of our testing is on cold-start recommending, our methods for recommending and evaluation are general.
ER  -