Authors:
Tinh Nguyen
1
;
2
;
Sang Vu
2
;
1
;
Truc Nguyen
1
;
2
;
Vuong Pham
3
;
2
;
4
and
Hien Nguyen
2
;
1
Affiliations:
1
University of Information Technology, Ho Chi Minh City, Vietnam
;
2
Vietnam National University, Ho Chi Minh City, Vietnam
;
3
Institute of Data Science and Artificial Intelligence, Sai Gon University, Ho Chi Minh City, Vietnam
;
4
University of Science, Ho Chi Minh City, Vietnam
Keyword(s):
Recommendation System, Consultation, Many-Cold-Start-Users, Nearest-Neighbors Approach, Intelligent System.
Abstract:
The real estate investment industry has experienced a significant increase in user participation over the years, with individuals keen on registering concurrent interests in both recent and prior projects. This growing trend necessitates the development of an approach that can recommend real estate items in a simultaneous manner. However, the presence of unrequired memberships and stop-by behaviors has introduced several challenges, resulting in numerous cold-start scenarios for new users. This study proposes a recommendation system tailored specifically for real estate, designed to offer warm-start item recommendations of cold-start users using a content-based approach and a session-based recommendation system. Herein, a system for real estate recommendation with acceptable warm-start item recommendations is proposed in the many-cold-start-users scenario. The session-based recommendation system is adapted and made use of pre-existing methods to effectively handle sequential and cont
extual data for the encoded attribute prediction of the next-interacted item. Then, the nearest-neighbors method is employed weighted cosine similarity to identify conforming candidates. The results demonstrate the effectiveness of efficiently integrating the information and the difficulty in performing well in item recommendations simultaneously.
(More)