KIPS Transactions on Computer and Communication Systems (정보처리학회논문지:컴퓨터 및 통신 시스템)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Recommendation System Based on Correlation Analysis of User Behavior Data in Online Shopping Mall Environment

온라인 쇼핑몰 환경에서 사용자 행동 데이터의 상관관계 분석 기반 추천 시스템

  • Received : 2023.11.10
  • Accepted : 2023.12.18
  • Published : 2024.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

As the online commerce market continues to expand with an increase of diverse products and content, users find it challenging in navigating and in the selection process. Thereafter both platforms and shopping malls are actively working in conducting continuous research on recommendations system to select and present products that align with user preferences. Most existing recommendation studies have relied on user data which is relatively easy to obtain. However, these studies only use a single type of event and their reliance on time dependent data results in issues with reliability and complexity. To address these challenges, this paper proposes a recommendation system that analysis user preferences in consideration of the relationship between various types of event data. The proposed recommendation system analyzes the correlation of multiple events, extracts weights, learns the recommendation model, and provides recommendation services through it. Through extensive experiments the performance of our system was compared with the previously studied algorithms. The results confirmed an improvement in both complexity and performance.

매년 증가하는 온라인 상거래 시장과, 점차 다양해지는 상품과 콘텐츠로 인해 사용자들은 선택 과정에 어려움을 느낀다. 이에 여러 기업들은 온라인 쇼핑몰에서 사용자가 선호할 상품을 선별하여 제공하기 위해 추천 시스템에 대한 지속적인 연구를 진행하고 있다. 대다수의 추천 시스템 연구에서는 비교적 획득하기 쉬운 사용자의 이벤트 데이터를 기반하여 연구를 진행하였으나 한 종류의 사용자 행동만을 고려하기 때문에 사용자의 선호도를 파악하는 것에 오차가 발생한다. 이에 본 논문에서는 여러 종류의 사용자 행동 데이터의 상관관계를 고려하여 사용자의 선호도를 분석하는 추천 시스템을 제안한다. 제안하는 추천 시스템은 사용자의 사용자 행동 데이터의 상관관계를 분석하고 가중치를 생성하여 추천 모델을 학습한다. 실험에서는 기존 연구의 알고리즘과의 성능 비교를 통해 제안하는 시스템의 복잡도와 성능 향상을 확인하였다.

Keywords

Acknowledgement

이 논문은 2022년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임(No. 2022-0-00218).

References

  1. D. Jannach, A. Manzoor, W. Cai, and L. Chen, "A survey on conversational recommender systems," ACM Computing Survey, Vol.54, No.105, pp.1-36, 2021.
  2. S. Milano, M. Taddeo, and L. Floridi, "Recommender systems and their ethical challenges," Ai & Society, Vol.35, pp.957-967, 2020.
  3. P. Convington, J. Adams, and E. Sargin, "Deep neural networks for YouTube recommendations," Proceedings of the 10th ACM Conference on Recommender Systems, pp.191-198, 2016.
  4. C. A. Gomez-Uribe and N. Hunt, "The netflix recommender system: Algorithms, business value, and innovation," ACM Transactions on Management Information Systems, Vol.6, No.13, pp.1-19, 2015.
  5. H. Cheng et al., "Wide & deep learning for recommender systems," Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp.7-10, 2016.
  6. P. Nagarnaik and A. Thomas, "Survey on recommendation system methods," 2015 2nd International Conference on Electronics and Communication Systems (ICECS), 2015.
  7. Y. Koren, "Recommender system utilizing collaborative filtering combining explicit and implicit feedback with both neighborhood and latent factor models," US patents, 2011.
  8. D. Yang, T. Chen, W. Zhang, Q. Lu, and Y. Yu, "Local implicit feedback mining for music recommendation," Proceedings of the sixth ACM Conference on Recommender Systems, pp.91-98, 2012.
  9. W. Pan, S. Xia, Z. Liu, X. peng, Z. Ming, "Mixed factorization for collaborative recommendation with heterogeneous explicit feedbacks," Information Sciences, Vol.332, pp.84-93, 2016.
  10. C. Zhang and C. Li, "Neural collaborative filtering recommendation algorithm based on popularity feature," Culture-oriented Science & Technology (ICCST), International Conference on, 2021.
  11. H. Ko, S. Lee, Y. Park, and A. Choi, "A survey of recommendation systems: Recommendation models, techniques, and application fields," Electronics, Vol.11, No.1, pp.141, 2022.
  12. S. Sidana, M. Trofimov, O. Horodnytskyi, Y. Maximov, and M. R. Amini, "User preference and embedding learning with implicit feedback for recommender systems," Data Mining and Knowledge Discovery, Vol.35, pp.568-592, 2021.
  13. X. Chen, L. Li, W. Pan, and Z. Ming, "A survey on heterogeneous one-class collaborative filtering," ACM Transactions on Information Systems, Vol.38, No.35, pp.1-54, 2020.
  14. E. R. N. Valdez, D. Quintana, R. G. Crespo, P. Isasi, and E. H. Viedma, "A recommender system based on implicit feedback for selective dissemination of ebooks," Information Sciences, Vol.467, pp.87-98, 2018.
  15. X. Su and T. M. Khoshgoftaar, "A survey of collaborative filtering techniques," Advances in Artificial Intelligence, 2009.
  16. Y. Koren, S. Rendle, and R. Bell, "Advances in collaborative filtering," Recommender Systems Handbook, pp.91-142, 2021.
  17. Y. Hu, Y. Koren, and C. Volinsky, "Collaborative filtering for implicit feedback datasets," 2008 Eighth IEEE International Conference on Data Mining, 2008.
  18. X. He, L. Liao, H. Zhang, L. Nie, and X. Hu, "Neural collaborative filtering," WWW '17: Proceedings of the 26th International Conference on World Wide Web, pp.173-182, 2017.
  19. Y. Li, S. Wang, Q. Pan, H. Peng, T. Yang, and E. Cambria, "Learning binary codes with neural collaborative filtering for efficient recommendation systems," Knowledge-Based Systems, Vol.172, pp.64-75, 2019.
  20. S. Rendle, W. Krichence, L. Zhang, and J. Anderson, "Neural collaborative filtering vs. matrix factorization revisited," Proceedings of the 14th ACM Conference on Recommender Systems, pp.240-248, 2020.
  21. S. Rendle, C. Freudenthaler, Z. Gantner, and L. S. Thieme, "BPR: Bayesian personalized ranking from implicit feedback," arxiv:1205.2618, 2012.
  22. W. Pan, H. Zhong, C. Xu, and Z. Ming, "Adaptive Bayesian personalized ranking for heterogeneous implicit feedbacks," Knowledge-Based Systems, Vol.73, pp.173-180, 2015.
  23. H. Qiu, Y. Liu, G. Guo, Z. Sun, J. Zhang, and H. T. Nguyen, "BPRH: Bayesian personalized ranking for heterogeneous implicit feedback," Information Sciences, Vol.453, pp. 80-98, 2018.
  24. C. Chen, M. Zhang, Y. Zhang, W. Ma, and S. Ma, "Efficient heterogeneous collaborative filtering without negative sampling for recommendation," AAAI-20 Technical, Vol.34, 2020.
  25. S. Debnath, N. Ganguly, and P. Mitra, "Feature weighting in content based recommendation system using social network analysis," WWW '08: Proceedings of the 17th international conference on World Wide Web, pp.1041-1042, 2008.
  26. B. Wang, Q. Liao, and C. Zhang, "Weight based KNN recommender system," 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, 2013.
  27. T. Himel, M. N. Uddin, M. A. Hossain, and Y. M. Jang, "Weight based movie recommendation system using Kmeans algorithm," 2017 International Conference on Information and Communication Technology Convergence (ICTC), 2017.
  28. Z. Cui et al., "Personalized recommendation system based on collaborative filtering for IoT scenarios," IEEE Transactions on Services Computing, Vol.13, 2020.
  29. U. Bhimavarapu, N. Chinalapudi, and G. Battineni, "A fair and safe usage drug recommendation system in medical emergencies by a stacked ANN," Algorithms, Vol.15, No.6, pp.186, 2022.
  30. L. Jiang, Y. Cheng, L. Yang, J. Li, H. Yan, and X. Wang, "A trust-based collaborative filtering algorithm for Ecommerce recommendation system," Journal of Ambient Intelligence and Humanized Computing, Vol.10, pp.3023-3034, 2019.
  31. Y. Guo, M. Wang, and X. Li, "An interactive personalized recommendation system using the hybrid algorithm model," Symmetry, Vol.9, No.10, pp.216, 2017.
  32. Beibei Dataset [Internet], https://github.com/dingjingtao/NegativeSamplerBPR/tree/master/BPRplusView/data/beibei
  33. Sobazaar Dataset [Internet], https://github.com/hainguyen-telenor/Learning-to-rank-from-implicit-feedback/tree/master/Data