Consumer-Oriented Multi-Party Matching Recommendation System Based Deep Learning
Woo Seok Seo, Jae Hyun Jun, Jong‐Il Kim, Tae Jin Bae, Dae Soo Kim · 2020
In this paper, we propose the consumer-oriented multi-party matching recommendation system based deep learning that recommends the most suitable participants to consumers when producing a work. The proposed method uses a deep learning model that takes the characteristics and constraints of the consumer as input. The deep learning model uses the Candidate Generation Model, which selects candidate candidates, and the Ranking Model, which recalculates the recommendation scores of selected candidate candidates. Therefore, a group of candidates suitable for a large candidate group is recommended.