Personalized Ranking Metric Embedding for Next New POI Recommendation
S. Feng, X. Li, Y. Zeng, G. Cong, Y. Chee, and Q. Yuan. Proceedings of the 24th International Conference on Artificial Intelligence, page 2069--2075. AAAI Press, (2015)
Abstract
The rapidly growing of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which enables many services, e.g., point-of-interest (POI) recommendation. In this paper, we study the next new POI recommendation problem in which new POIs with respect to users' current location are to be recommended. The challenge lies in the difficulty in precisely learning users' sequential information and personalizing the recommendation model. To this end, we resort to the Metric Embedding method for the recommendation, which avoids drawbacks of the Matrix Factorization technique. We propose a personalized ranking metric embedding method (PRME) to model personalized check-in sequences. We further develop a PRME-G model, which integrates sequential information, individual preference, and geographical influence, to improve the recommendation performance. Experiments on two real-world LBSN datasets demonstrate that our new algorithm outperforms the state-of-the-art next POI recommendation methods.
%0 Conference Paper
%1 feng2015personalized
%A Feng, Shanshan
%A Li, Xutao
%A Zeng, Yifeng
%A Cong, Gao
%A Chee, Yeow Meng
%A Yuan, Quan
%B Proceedings of the 24th International Conference on Artificial Intelligence
%D 2015
%I AAAI Press
%K POI diss embedding inthesis lme logistic markov prediction ranking recommendation
%P 2069--2075
%T Personalized Ranking Metric Embedding for Next New POI Recommendation
%U http://dl.acm.org/citation.cfm?id=2832415.2832536
%X The rapidly growing of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which enables many services, e.g., point-of-interest (POI) recommendation. In this paper, we study the next new POI recommendation problem in which new POIs with respect to users' current location are to be recommended. The challenge lies in the difficulty in precisely learning users' sequential information and personalizing the recommendation model. To this end, we resort to the Metric Embedding method for the recommendation, which avoids drawbacks of the Matrix Factorization technique. We propose a personalized ranking metric embedding method (PRME) to model personalized check-in sequences. We further develop a PRME-G model, which integrates sequential information, individual preference, and geographical influence, to improve the recommendation performance. Experiments on two real-world LBSN datasets demonstrate that our new algorithm outperforms the state-of-the-art next POI recommendation methods.
%@ 978-1-57735-738-4
@inproceedings{feng2015personalized,
abstract = {The rapidly growing of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which enables many services, e.g., point-of-interest (POI) recommendation. In this paper, we study the next new POI recommendation problem in which new POIs with respect to users' current location are to be recommended. The challenge lies in the difficulty in precisely learning users' sequential information and personalizing the recommendation model. To this end, we resort to the Metric Embedding method for the recommendation, which avoids drawbacks of the Matrix Factorization technique. We propose a personalized ranking metric embedding method (PRME) to model personalized check-in sequences. We further develop a PRME-G model, which integrates sequential information, individual preference, and geographical influence, to improve the recommendation performance. Experiments on two real-world LBSN datasets demonstrate that our new algorithm outperforms the state-of-the-art next POI recommendation methods.},
acmid = {2832536},
added-at = {2017-01-18T10:53:17.000+0100},
author = {Feng, Shanshan and Li, Xutao and Zeng, Yifeng and Cong, Gao and Chee, Yeow Meng and Yuan, Quan},
biburl = {https://www.bibsonomy.org/bibtex/2a4e4b998752c3aee0dd57210a189561a/becker},
booktitle = {Proceedings of the 24th International Conference on Artificial Intelligence},
interhash = {a403db879ff0a5642949f84ea87bbb8f},
intrahash = {a4e4b998752c3aee0dd57210a189561a},
isbn = {978-1-57735-738-4},
keywords = {POI diss embedding inthesis lme logistic markov prediction ranking recommendation},
location = {Buenos Aires, Argentina},
numpages = {7},
pages = {2069--2075},
publisher = {AAAI Press},
series = {IJCAI'15},
timestamp = {2017-01-18T10:53:32.000+0100},
title = {Personalized Ranking Metric Embedding for Next New POI Recommendation},
url = {http://dl.acm.org/citation.cfm?id=2832415.2832536},
year = 2015
}