KIISE Transactions on Computing Practices (정보과학회 컴퓨팅의 실제 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Evaluation of Recurrent Neural Network Algorithms for Recommendation System in E-commerce

전자상거래 추천시스템을 위한 순환신경망 알고리즘들의 성능평가

  • 서지혜 (이화여자대학교 컴퓨터공학과) ;
  • 용환승 (이화여자대학교 컴퓨터공학과)
  • Received : 2017.02.28
  • Accepted : 2017.05.12
  • Published : 2017.07.15
⟨ Previous Next ⟩

Abstract

Due to the advance of e-commerce systems, the number of people using online shopping and products has significantly increased. Therefore, the need for an accurate recommendation system is becoming increasingly more important. Recurrent neural network is a deep-learning algorithm that utilizes sequential information in training. In this paper, an evaluation is performed on the application of recurrent neural networks to recommendation systems. We evaluated three recurrent algorithms (RNN, LSTM and GRU) and three optimal algorithms(Adagrad, RMSProp and Adam) which are commonly used. In the experiments, we used the TensorFlow open source library produced by Google and e-commerce session data from RecSys Challenge 2015. The results using the optimal hyperparameters found in this study are compared with those of RecSys Challenge 2015 participants.

전자상거래 발전에 따라 온라인 쇼핑을 이용하는 사람들이 증가하였고 제품 또한 다양해지고 있다. 이러한 추세로 구매자가 만족할 수 있는 정확한 추천시스템의 중요성이 증대되었으며 정확도를 높이기 위한 새로운 방법의 연구가 계속되고 있다. 순환신경망은 시퀀스 학습에 적합한 딥 러닝 방법 중 하나이며 본 연구에서는 추천시스템의 정확도를 높이는 방법으로 구매자의 제품 접근순서를 순환신경망에 적용하여 알고리즘 성능평가를 하였다. 알고리즘 성능평가에는 대표적인 순환신경망 알고리즘과 최적화 알고리즘으로 진행하였다. 순환신경망 알고리즘으로는 RNN, LSTM, GRU 그리고 최적화 알고리즘으로는 Adagrad, RMSProp, Adam optimizer를 사용하였다. 실험 도구로는 구글의 오픈소스 라이브러리인 텐서플로우를 사용하였고 데이터는 RecSys Challenge 2015에서 제공하는 e-commerce session 데이터를 활용하였다. 실험 결과 실험 데이터에 적합한 최적의 하이퍼파라미터를 발굴하고 적용하여 RecSys Challenge 2015 참가자들의 결과와 비교하였다. 상품 접근 순서만을 학습시킨 결과이기 때문에 등수가 높지는 않았지만 기존 추천시스템에 접목한다면 정확도 향상에 기여할 수 있을 것으로 보인다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. J. Son, S. Kim, H. Kim, and S. Cho, "Review and Analysis of Recommender Systems," Journal of KIIE, Vol. 41, No. 2, pp. 185-208, Apr. 2015. (in Korean)
  2. B. M. Sarwar, G. Karypis, J. A. Konstan, and J. T. Riedl, "Analysis of Recommendation Algorithms for E-commerce," Proc. of 2nd ACM Conference on Electronic Commerce, pp. 158-167, 2000.
  3. B. Hidasi, A. Karatzoglou, L. Baltrunas, and D. Tikk, "Session-based Recommendations with Recurrent Neural Networks," Proc. of the ICLR 2016, 2016.
  4. S. Wu, W. Ren, C. Yu, G. Chen, D. Zhang, and J. Zhu, "Personal Recommendation Using Deep Recurrent Neural Network in NetEase," Proc. of the 32nd ICDE 2016, 2016.
  5. I. Sutskever, "Training Recurrent Neural Netwroks," PhD thesis Uninversity Tronto, 2012.
  6. Y. H. Wu and A. L. Chen, "Index structures of user profiles for efficient web page filtering services," Proc. of the 20th International Conference on Distributed Computing Systems, pp. 644-644, 2000.
  7. G. Linden, B. Smith, and J. York, "Amazon. com recommendations: Item-to-item collaborative fitering," Journal of IEEE Internet Computing, Vol. 7, No. 1, pp. 76-80, Feb. 2003. https://doi.org/10.1109/MIC.2003.1167344
  8. J. Seo, H. Yong, "Performance Evaluation of LSTM and GRU using TensorFlow," Proc. of the KIISE 2016 winter, pp. 211-213, 2016. (in Korean)
  9. Y. Bengio, P. Simard, and P. Frasconi, "Learning Long-Term Dependencies with gradient descent is difficult," Journal of IEEE Transactions on Neural Networks, Vol. 5, No. 2, pp. 157-166, Mar. 1994. https://doi.org/10.1109/72.279181
  10. S. Hochreiter and J. Schmidhuber, "Long short-term memory," Joural of Neural Computation, Vol. 9, No. 8, pp. 1735-1780, Nov. 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  11. K. Cho, B. van Merrienboer, C. Gulcehre, F. Bougares, H. Schwenk, and Y, Bengio, "Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation," Proc. of the EMNLP 2014, pp. 1724-1734, Sep. 2014.
  12. J. Duchi, E. Hazan, and Y. Singer, "Adaptive Subgradient Methods for Online Learning and Stochastic Optimization," Journal of Machine Learning Research, 12, pp. 2121-2159, Jul. 2011.
  13. T. Tieleman and G. Hinton, "Lecture 6.5 - RMSProp, COURSERA : Neural Networks for Machine Learning," Technical report.
  14. D. Kingma and J. Ba, "Adam : A method for stochastic optimization," Proc. of the ICLR 2015, arXvi, pp. 1412-6980, 2015.
  15. D. Ben-Shimon, A. Tsikinovsky, M. Friedmann, B. Shapira, L. Rokach, and J. Hoerle, "RecSys Challenge 2015 and the YOOCHOOSE Dataset," Proc. of the ACM RecSys 2015, pp. 357-358, 2015.
  16. J. Seo. (1993, Feb 28). RecSys Challenge 2015 [Online]. Available: http://2015.recsyschallenge.com/ submission.html (downloaded 2016, Sep. 30)