KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning-Based Personalized Recommendation Using Customer Behavior and Purchase History in E-Commerce

전자상거래에서 고객 행동 정보와 구매 기록을 활용한 딥러닝 기반 개인화 추천 시스템

  • 홍다영 (고려대학교 의학통계학협동과정) ;
  • 김가영 (성균관대학교 인공지능학과) ;
  • 김현희 (동덕여자대학교 정보통계학과)
  • Received : 2021.10.15
  • Accepted : 2021.11.18
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we present VAE-based recommendation using online behavior log and purchase history to overcome data sparsity and cold start. To generate a variable for customers' purchase history, embedding and dimensionality reduction are applied to the customers' purchase history. Also, Variational Autoencoders are applied to online behavior and purchase history. A total number of 12 variables are used, and nDCG is chosen for performance evaluation. Our experimental results showed that the proposed VAE-based recommendation outperforms SVD-based recommendation. Also, the generated purchase history variable improves the recommendation performance.

본 논문은 고객의 온라인 행동 정보와 구매 기록을 활용하여 기존의 추천 시스템이 갖는 데이터 희소성의 문제와 콜드 스타트 문제를 해결하고자 VAE 기반 추천 시스템을 제시하였다. 고객의 구매 기록을 임베딩하고 차원 축소하여 단일 변수로 생성하였으며, 온라인 행동 정보를 활용하여 학습을 통해 고객의 잠재 요인을 추출하는데 Variational Autoencoders를 적용하였다. VAE 기반 추천 시스템은 총 12개의 고객의 특성 변수에 VAE를 적용하여 저차원의 벡터를 생성한 뒤 이를 통해 유사 사용자를 찾은 다음, 유사 사용자들이 구매했던 상품들을 고객에게 추천한다. 이렇게 추천한 상품들의 점수를 매겨 nDCG로 성능을 평가하였다. 실험 결과 구매 기록 변수 그리고 온라인 행동 로그 변수를 활용한 VAE 기반의 추천시스템이 SVD 기반의 추천 시스템보다 성능이 좋다는 것을 알 수 있었다. 따라서 고객의 온라인 행동 로그 및 구매 기록을 사용하여 상품을 추천하면 정보 수집에 발생하는 비용과 시간을 줄일 수 있을 뿐만이 아니라 기존 추천 시스템보다 더욱 효율적으로 상품을 추천할 수 있다는 것을 보여주었다.

Keywords

Acknowledgement

이 논문은 2020년도 동덕여자대학교 학술연구비 지원에 의하여 수행된 것임.

References

  1. S. Zhang, L. Yao, A. Sun, and Y. Tay, "Deep learning based recommender system: A survey and new perspectives," ACM Computing Surveys, Vol.1, No.1, pp.1-35, 2018. https://doi.org/10.1145/356540.356541
  2. R. Mu, X. Zeng, and L. Han, "A survey of recommender systems based on deep learning," IEEE Access, Vol.6, pp. 69009-69022, 2018. https://doi.org/10.1109/access.2018.2880197
  3. A. Da'u and N. Salim, "Recommendation system based on deep learning methods: A systematic review and new directions," Artificial Intelligence Review, Vol.53, No.4, pp.2709-2847, 2020. https://doi.org/10.1007/s10462-019-09744-1
  4. Y. Koren, R. Bell, and C. Volinsky, "Matrix Factorization Techniques for Recommender Systems," IEEE Computer, Vol. 42, No.8, pp.30-37, 2009.
  5. S. Sedhain, A. K. Menon, S. Scanner, and L. Xie, "AutoRec: Autoencoders meet collaborative filtering," In Proceedings of the 24th International Conference on World Wide Web, May 2015.
  6. H. J. Xue, X. Y. Dai, J. Zhang, S. Huang, and J. Chen, "Deep matrix factorization models for recommender systems," In Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp.3203-3209, 2017.
  7. D. P. Kingma, "Auto-encoding variational bayes," In Proceedings of the 2nd International Conference on Learning Representations (ICLR), Apr. 2014.
  8. D. Liang, R. G. Krishnan, M. D. Hoffman, and T. Jebara, "Variational autoencoders for collaborative filtering," In Proceedings of the 24th International Conference on World Wide Web, Apr. 2018.
  9. I. Shenbin, A. Alekseev, E. Tutubalina, V. Malykh, and S. I. Nikolenko, "RecVAE: A new variational autoencoder for Top-N recommendations with implicit feedback," In Proceedings of the Web Search and Data Mining , Feb. 2020.
  10. X. He, L. Liao, H. Zhang, L. Nie, X. Hu, and T-S Chua, "Neural collaborativ filtering," In Proceedings of the International Conference on World Wide Web, Apr. 2017.
  11. Y. Wang, L. Wang, Y. Li, D. He, T. Y. Liu, and W. Chen, "A Theoretical Analysis of NDCG Ranking Measures," In Proceedings of 26th Annual Conference on Learning Theory, 2013.
  12. G. Kim, J. Kwak, D. Hong, and H. H. Kim, "A variational autoencoders based recommendation using the online behavior log," In Proceedings of the Korean Institute of Information Scientists and Engineers, pp.1147-1149, 2020.
  13. Y. Jung and Y. Cho, "Topic modeling-based book recommendations considering online purchase behavior," Knowledge Management Research, Vol.18, No.4, pp.97-118, 2017.
  14. H. Lee, S. Hong, J. Bang, and H. Kim, "A study on the music recommendation based on user playlist using data embedding," The Journal of Korean Institute of Information Technology, Vol.18, No.9, pp.27-34, 2020. https://doi.org/10.14801/jkiit.2020.18.9.27
  15. Y. Guan, Q. Wei, and G. Chen, "Deep learning based personalized recommendation with multi-view information integration," Decision Support Systems, Vol.118, pp.58-69, 2019. https://doi.org/10.1016/j.dss.2019.01.003
  16. X. Li and J. She, "Collaborative variational autoencoder for recommender systems," In Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2017.
  17. D. P. Kingma and M. Welling, "An introduction to variational autoencoders," Foundations and Trends in Machine Learning, Vol.12, No.4, pp.15-32, 2019.
  18. M. G. Kim and K. Kim, "Recommender systems using SVD with social network information," Journal of Intelligent Information Systems, Vol.22, No.4, pp.1-18, 2016.
  19. Y. Wang, L. Wang, Y. Li, D. He, W. Chen, and T. Y. Liu, "A theoretical analysis of normalized discounted cumulative gain (NDCG) ranking measures," In Proceedings of the 26th Annual Conference on Learning Theory (COLT), 2013.
  20. K. Jaevelin and J. Kekaelaeinen, "Cumulated gain-based evaluation of IR techniques," ACM Transactions on Information Systems, Vol.20, No.4, pp.422-446, 2022. https://doi.org/10.1145/582415.582418