대한건축학회논문집 (Journal of the Architectural Institute of Korea)

  • 제36권11호
  • /
  • Pages.163-170
  • /
  • 2020
  • /
  • 2733-6239(pISSN)
  • /
  • 2733-6247(eISSN)
대한건축학회 (Architectural Institute of Korea)
권호 표지
DOI QR코드

DOI QR Code

주거의사결정지원을 위한 임베딩 기반 협력필터링 추천시스템

Embedding-based Collaborative Filtering Recommender System for Supporting Housing Decision Making

  • 김재희 ((주)에코시안 기술연구소) ;
  • 장선우 ((주)종합건축사사무소가람건축) ;
  • 이득영 ((주)종합건축사사무소가람건축) ;
  • 전한종 (한양대 건축학과)
  • 투고 : 2020.09.23
  • 심사 : 2020.11.09
  • 발행 : 2020.11.30
⟨ 이전 논문 다음 논문 ⟩

초록

In the era of the 4th Industrial Revolution, a user-customized service recommendation system has been gaining attention in the terms of ultra-personalization, which collects and analyzes customer information in real time to increase satisfaction through reflecting the user's preference. In line with this global trend, various studies have been conducted to reflect the user's perspective through the analysis of housing preferences to support the housing decision-making process and improve service satisfaction. Unlike the previous studies that analyze the groups' housing preferences according to demographic and sociological characteristics, this study subdivided the analysis targets into the individuals to enable the derivation of housing preferences and the recommendation of customized housing alternatives. The purpose of this paper is to analyze the preferences of individual users by establishing an embedding-based residential recommendation system. Through this, it was intended to support a custom housing decision-making process from the individual user's point of view and to suggest one way to improve design quality as well as increase satisfaction in the architectural planning and design phase from the supplier's point of view.

키워드

과제정보

본 연구는 2020년도 국토교통부 도시건축 개발사업의 연구비지원(20AUDP-B127891-04)에 의해 수행되었습니다.

참고문헌

  1. Park, M., & Lee, D. (2017). Current Status and Implications of Manufacturing and Service Industry Linkages in Major Countries in the 4th Industrial Revolution, Report, Sejong Institute
  2. Jo, M. (2019). 4th Industrial Revolution, Marketing Research by Philip Kotler, Steel Research Center
  3. Schafer, B., & Konstan, J. (2000). E-Commerce Recommendation Applications,  Data Mining & Knowledge Discovery
  4. Goldberg, D., Nichols, D., Oki, B., & Terry, D. (1992). Using collaborative filtering to weave an information tapestry, Communications of the ACM - Special issue on information filtering, 35(12), 61-70
  5. Su, X., & Khoshgoftaar T. (2009). A survey of collaborative filtering techniques, Advances in Artificial Intelligence, 4
  6. Herlocker, J., Konstan, J., & Reidl, J. (2000). Explaining Collaborative Filtering Recommendations, Proceedings of the ACM Conference on Computer Supported Cooperative Work
  7. Ozsoy, M. (2016). From Word Embeddings to Item Recommendation, arXiv
  8. Yang, Z., He, J., & He, S. (2019). A Collaborative filtering Method based on Forgetting Theory And Neural Item Embedding, 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference, 1606-1610
  9. Earl W. Morris, M., & W. G. (1978). Housing, Family, and Society. New York: Wiley, 378, Volume 57, p.1021-1022
  10. Wang, C., & Wood, L. (2018). Liang, Huijun.Open House International; Gateshead, 43(3), p.33-42. https://doi.org/10.1108/OHI-03-2018-B0005
  11. Molin, E., Oppewal, H., & Timmermans, H. (1996). Predicting consumer response to new housing: A stated choice experiment, Journal of Housing and The Built Environment, 11, 297-311 https://doi.org/10.1007/BF02496593
  12. Ozsoy, M. (2016). From Word Embeddings to Item Recommendation, arXiv
  13. Yang, Z., He, J., & He, S. (2019). A Collaborative filtering Method based on Forgetting Theory And Neural Item Embedding, 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference, 1606-1610
  14. Seoul Open Data Plaza, (2020), Main Administrative Statistics,https://data.seoul.go.kr/together/statbook/statbookList.do#submenu25, 2020
  15. Jeong S., & & Choi, M. (2017). A study on the housing selection characteristics of eco-generation. Residential Environment, 15(1), p. 113-133. https://doi.org/10.22313/reik.2017.15.1.113
  16. Son, J., & Lee, B.(2017). A Study on Characteristics of Apartment Housing Preference according to Lifestyle. Residential Environment, 15(4), p.151-161. https://doi.org/10.22313/reik.2017.15.4.151
  17. Lee. J., & Kim, J. (2014). The effect of apartment environment properties on consumer preference: a conjoint analysis of view quality and park accessibility. Marketing Management Research, 19(2), p.91-109.
  18. Kim, T., Kwon, E., Choi, & Hong, S. (2013). A study on changes in housing demand by region through analysis of housing satisfaction & preference. Gyeonggi Institute Basic Research
  19. Kim, Y., & Seo, J. (2013). Analysis of residential preference characteristics according to the aging of the baby boomers. Residential Environment, 11, p.37-49.
  20. Lee, H., Park, H., & Go, S. (2009). A study on the preference of residential environment when purchasing apartments through conjoint analysis. Journal of the Korean Housing Association, 20(2), p. 27-35.
  21. Kim, J., & Lee, J. (2014). The effect of apartment environment properties on consumer preference: Conjoint analysis of view quality and park accessibility. Marketing Management Research, 19(2), p.91-109.
  22. Article 3 (1) 1 of the Enforcement Decree of the Korean Housing Act and Article 3-5 of the Enforcement Decree of the Building Act.
  23. Green, P., & Krieger, A. (1993). Conjoint analysis with product-positioning applications Handbooks in Operations Research and Management Science, pp. 467-515
  24. Jun, H., Kim, J., Rhee, D., & Chang, S. (2020). "SeoulHouse2Vec": An Embedding-Based Collaborative Filtering Housing Recommender System for Analyzing Housing Preference. Sustainability, 12, 6964. https://doi.org/10.3390/su12176964