User-to-User Matching Services through Prediction of Mutual Satisfaction Based on Deep Neural Network

다국어 초록 (Multilingual Abstract)

With the development of the sharing economy, existing recommender services are changing from user–itemrecommendations to user–user recommendations. The most important consideration is that all users shouldhave the best possible satisfaction. To achieve this outcome, the matching service adds information betweenusers and items necessary for the existing recommender service and information between users, so higher-leveldata mining is required. To this end, this paper proposes a user-to-user matching service (UTU-MS) employingthe prediction of mutual satisfaction based on learning. Users were divided into consumers and suppliers, andthe properties considered for recommendations were set by filtering and weighting. Based on this process, weimplemented a convolutional neural network (CNN)–deep neural network (DNN)-based model that can predicteach supplier’s satisfaction from the consumer perspective and each consumer’s satisfaction from the supplierperspective. After deriving the final mutual satisfaction using the predicted satisfaction, a top recommendationlist is recommended to all users. The proposed model was applied to match guests with hosts using Airbnb data,which is a representative sharing economy platform. The proposed model is meaningful in that it has beenoptimized for the sharing economy and recommendations that reflect user-specific priorities.

참고문헌 (Reference)

1 이오준 ; 유은순, "추천 시스템의 성능 안정성을 위한 예측적 군집화 기반 협업 필터링 기법" 한국지능정보시스템학회 21 (21): 119-142, 2015

2 소경영 ; 이윤한 ; 문경희 ; 고광만, "양방향 추천 캘리콘텐츠 오픈마켓 플랫폼 설계" 한국멀티미디어학회 18 (18): 1586-1593, 2015

3 이현호 ; 이원진, "사용자 피드백 정보 기반의 학습된 생활 스포츠 팀추천 서비스 시스템 설계 및 구현" 한국멀티미디어학회 21 (21): 242-249, 2018

4 H. T. Cheng, "Wide & deep learning for recommender systems" 7-10, 2016

5 C. Narasimhan, "Sharing economy : review of current research and future directions" 5 (5): 93-106, 2018

6 P. Xia, "Reciprocal recommendation system for online dating" 234-241, 2015

7 김진아 ; 문남미, "Rating and Comments Mining Using TF-IDF and SO-PMI for Improved Priority Ratings" 한국인터넷정보학회 13 (13): 5321-5334, 2019

8 R. Burke, "Patterns of multistakeholder recommendation"

9 O. Surer, "Multistakeholder recommendation with provider constraints" 54-62, 2018

10 Khamphaphone Xinchang ; Phonexay Vilakone ; 박두순, "Movie Recommendation Algorithm Using Social Network Analysis to Alleviate Cold-Start Problem" 한국정보처리학회 15 (15): 616-631, 2019

11 Chunyong Yin, "Mobile marketing recommendation method based on user location feedback" Springer Science and Business Media LLC 9 (9): 2019

12 L. Zheng, "Joint deep modeling of users and items using reviews for recommendation" 425-434, 2017

13 T. R. Kacchi, "Friend recommendation system based on lifestyles of users" 682-685, 2016

14 F. Yu, "Friend recommendation considering preference coverage in location-based social networks" 91-105, 2017

15 H. Song, "Eye-tracking and social behavior preference-based recommendation system" 75 (75): 1990-2006, 2019

16 Y. Yun, "Developing a hybrid collaborative filtering recommendation system with opinion mining on purchase review" 44 (44): 331-344, 2018

17 F. Liu, "Deep reinforcement learning based recommendation with explicit user-item interactions modeling"

18 S. Zhang, "Deep learning based recommender system : a survey and new perspectives" 52 (52): 1-38, 2019

19 J. Wei, "Collaborative filtering and deep learning based recommendation system for cold start items" 69 : 29-39, 2017

20 H. Wang, "Collaborative deep learning for recommender systems" 1235-1244, 2015

21 H. Abdollahpouri, "Beyond personalization: research directions in multistakeholder recommendation"

22 Phonexay Vilakone, "An Efficient movie recommendation algorithm based on improved k-clique" Springer Science and Business Media LLC 8 (8): 2018

23 M. Fu, "A novel deep learning-based collaborative filtering model for recommendation system" 49 (49): 1084-1096, 2018

24 E. C. Malthouse, "A multistakeholder recommender systems algorithm for allocating sponsored recommendations" 2019

25 오세창 ; 최민, "A Simple and Effective Combination of User-Based and Item-Based Recommendation Methods" 한국정보처리학회 15 (15): 127-136, 2019