Improving the Personalized Recommendation in the Cold-start Scenarios

被引：1

作者：

Gaspar, Peter ^{[1
]}

Koncal, Matej ^{[1
]}

Kompan, Michal ^{[1
]}

Bielikova, Maria ^{[1
]}

机构：

[1] Slovak Univ Technol Bratislava, Ilkovicova 2, Bratislava, Slovakia

来源：

2019 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA 2019) | 2019年

关键词：

personalized recommendation; cold-start; machine learning; collaborative filtering;

D O I：

10.1109/DSAA.2019.00079

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Recommender systems generate items that should be interesting for the customers. However, recommenders usually fail in the cold-start scenario - when a new item or a new customer appears. In our work, we study the cold-start problem for a new customer. For a cold-start customer we find the most similar customers and use a "their" pre-trained collaborative filtering model to recommend. We compare several recommendation approaches and similarity metrics to analyze the accuracy and computational performance.

引用

页码：606 / 607

页数：2

共 4 条

[1]

[Anonymous], 2015, Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th

[2]

Cremonesi Paolo., 2009, RECSYS, P233

[3]

Park S.-T., 2009, P 3 ACM C REC SYST A, P21, DOI DOI 10.1145/1639714.1639720

[4] Cold-start News Recommendation with Domain-dependent Browse Graph [J].

Trevisiol, Michele ;

Aiello, Luca Maria ;

Schifanella, Rossano ;

Jaimes, Alejandro .

PROCEEDINGS OF THE 8TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'14), 2014, :81-88

← 1 →