Research on the Solutions to Cold-Start Problems
- 10.2991/978-2-38476-062-6_3How to use a DOI?
- Cold-Start; NeuralCF; AutoRec; DropoutNet
The recommender system has seeped into each corner of the earth, but any recommender system has to experience the process of lacking data at the beginning. So, how to recommend things well in that condition becomes a cold start problem. The recommendation system cold start problem has always been a big problem in recommendation systems. Many different algorithms are developed in order to better solve the problem. The cold start problem is studied in this paper. The authors try to use neural co-filtering, autoRec and DropoutNet to study this. By comparing different methods to deal with data without project characteristics or user characteristics, it is concluded that DropoutNet has made some improvements to the dataset with new uses or projects.
- © 2023 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Yuehan Qin AU - Wuji Chang AU - Songtao Zhang AU - Yihuan Yan PY - 2023 DA - 2023/07/11 TI - Research on the Solutions to Cold-Start Problems BT - Proceedings of the 2023 2nd International Conference on Social Sciences and Humanities and Arts (SSHA 2023) PB - Atlantis Press SP - 12 EP - 18 SN - 2352-5398 UR - https://doi.org/10.2991/978-2-38476-062-6_3 DO - 10.2991/978-2-38476-062-6_3 ID - Qin2023 ER -