A scalable, high-performance Algorithm for hybrid job recommendations
作者： Toon De Pessemier , Kris Vanhecke , Luc Martens
关键词:
摘要: Recommender systems can be used as a tool to assist people in finding job. However, this specific domain requires expert algorithms with knowledge recommend jobs conformable people's expertise and interests. This is the topic of Recsys Challenge 2016, which aims for an algorithm that predicts job postings user will positively interact with. Our solution hybrid combining content-based KNN approach. The matches features candidate recommendations historical interactions. approach searches are most similar interacted past. resulting combination lightweight fast scalable, generating proper evaluation score.
core.ac.uk
acm.org
sci-hub.se 参考文章(5)
Simon Dooms, Luc Martens, Toon De Pessemier, A user-centric evaluation of recommender algorithms for an event recommendation system conference on recommender systems. pp. 67- 73 ,(2011)
Wenxing Hong, Siting Zheng, Huan Wang, Dynamic user profile-based job recommender system international conference on computer science and education. pp. 1499- 1503 ,(2013) , 10.1109/ICCSE.2013.6554164
Mamadou Diaby, Emmanuel Viennet, Tristan Launay, Toward the next generation of recruitment tools: an online social network-based job recommender system advances in social networks analysis and mining. pp. 821- 828 ,(2013) , 10.1145/2492517.2500266
Tony C. Smith, Eibe Frank, Introducing Machine Learning Concepts with WEKA Methods in Molecular Biology. ,vol. 1418, pp. 353- 378 ,(2016) , 10.1007/978-1-4939-3578-9_17
Fabian Abel, András Benczúr, Daniel Kohlsdorf, Martha Larson, Róbert Pálovics, RecSys Challenge 2016: Job Recommendations conference on recommender systems. pp. 425- 426 ,(2016) , 10.1145/2959100.2959207