%0 Conference Paper %1 xiao2016recommendation %A Xiao, Wenming %A Xu, Xiao %A Liang, Kang %A Mao, Junkang %A Wang, Jun %B Proceedings of the Recommender Systems Challenge %C New York, NY, USA %D 2016 %I ACM %K 2016 Hawkes challenge job process recommendation recsys sys:toRead %P 11:1--11:4 %R 10.1145/2987538.2987543 %T Job Recommendation with Hawkes Process: An Effective Solution for RecSys Challenge 2016 %U http://doi.acm.org/10.1145/2987538.2987543 %X The RecSys Challenge 2016 focuses on the prediction of users' interest in clicking a job posting in the career-oriented social networking site Xing. Given users' profile, the content of the job posting, as well as the historical activities of users, we aim in recommending top job postings to users for the coming week. This paper introduces the winning strategy for such a recommendation task. We summarize several key components that result in our leading position in this contest. First, we build a hierarchical pairwise model with ensemble learning as the overall prediction framework. Second, we integrate both content and behavior information in our feature engineering process. In particular, we model the temporal activity pattern using a self-exciting point process, namely Hawkes Process, to generate the most relevant recommendation at the right moment. Finally, we also tackle the challenging cold start issue using a semantic based strategy that is built on the topic modeling with the users profiling information. Our approach achieved the highest leader-board and full scores among all the submissions. %@ 978-1-4503-4801-0

@inproceedings{xiao2016recommendation, abstract = {The RecSys Challenge 2016 focuses on the prediction of users' interest in clicking a job posting in the career-oriented social networking site Xing. Given users' profile, the content of the job posting, as well as the historical activities of users, we aim in recommending top job postings to users for the coming week. This paper introduces the winning strategy for such a recommendation task. We summarize several key components that result in our leading position in this contest. First, we build a hierarchical pairwise model with ensemble learning as the overall prediction framework. Second, we integrate both content and behavior information in our feature engineering process. In particular, we model the temporal activity pattern using a self-exciting point process, namely Hawkes Process, to generate the most relevant recommendation at the right moment. Finally, we also tackle the challenging cold start issue using a semantic based strategy that is built on the topic modeling with the users profiling information. Our approach achieved the highest leader-board and full scores among all the submissions.}, acmid = {2987543}, added-at = {2017-03-23T10:59:27.000+0100}, address = {New York, NY, USA}, articleno = {11}, author = {Xiao, Wenming and Xu, Xiao and Liang, Kang and Mao, Junkang and Wang, Jun}, biburl = {https://www.bibsonomy.org/bibtex/25baacd8970413103cd68b5afc6f3e8d6/nosebrain}, booktitle = {Proceedings of the Recommender Systems Challenge}, description = {Job recommendation with Hawkes process}, doi = {10.1145/2987538.2987543}, interhash = {cce3df0e5552f27803e34922d06e1026}, intrahash = {5baacd8970413103cd68b5afc6f3e8d6}, isbn = {978-1-4503-4801-0}, keywords = {2016 Hawkes challenge job process recommendation recsys sys:toRead}, location = {Boston, Massachusetts}, numpages = {4}, pages = {11:1--11:4}, publisher = {ACM}, series = {RecSys Challenge '16}, timestamp = {2017-03-23T10:59:44.000+0100}, title = {Job Recommendation with Hawkes Process: An Effective Solution for RecSys Challenge 2016}, url = {http://doi.acm.org/10.1145/2987538.2987543}, year = 2016 }