序列推薦系統的目的是以用戶過往購買紀錄所形成的序列，預測用戶在下一次購買時有興趣的商品。過往的推薦系統由於僅考慮商品項目層級的關聯性，因此忽略了商品類別層級的購買間隔資訊。本論文擴展 TiSASRec 模型，提出了兩個可將類別資訊加入到用戶購買紀錄中的模型: TiSASRecC 及TiSASRecDual，TiSASRecC 模型採用將商品項目嵌入向量表示法與商品類別嵌入向量表示法接合，使類別資訊直接融入到商品表示法中輔助模型學習用戶行為表示法。TiSASRecDual 模型則以類別層級子網路先單獨學習商品類別結合時間間隔的用戶行為特徵，再以學習出的子分類層級特徵，間接影響項目層級子網路中用戶行為表示法的學習。在 Amazon 五個不同性質的類別資料集上之實驗結果顯示:加入類別資訊對序列推薦任務有所提升。本研究提出的兩個模型，在用戶序列長度取樣減短時比 TiSASRec 模型有更佳的推薦效果，而透過將用戶多個類別的購買紀錄形成的序列對模型進行訓練及預測，對單一類別的商品的推薦效果也比 TiSASRec 有更明顯的增進效果。

The purpose of a sequential recommendation system is to predict the product that the user is interested in the next purchase based on the sequence of the user's past purchasing records. Most of the previous studies on sequential recommendation systems only considered patterns of item level and ignored information of category level. This thesis extends the TiSASRec model and proposes two models, named TiSASRecC and TiSASRecDual, respectively, to effectively combine category information into the representation of user purchase records. TiSASRecC model concatenates the embeddings of item and its category to make the category information integrated into the representation of purchase record explicitly to learn better representation of user behavior. TiSASRecDual model uses a category-level subnetwork to learn the patterns of product categories combined with time intervals of purchases. The category-level representation of user behavior implicitly affects the representation of item level. The experiments on the datasets of Amazon with various product categories show that using category information additionally improves the hit ratio of the sequential recommendation tasks. The proposed two models’ better performances than the TiSASRec model when the user sequence length sampling is shortened. Besides, by comparing to using records of a single category, after combining purchase records of the same user on multiple product categories for training and testing, the hit ratios of the proposed models have more significant improvement than TiSASRec.

[1] Rendle, S., Freudenthaler, C., & Schmidt-Thieme, L. (2010, April). Factorizing personalized markov chains for next-basket recommendation. In Proceedings of the 19th international conference on World wide web (pp. 811-820).
[2] Tang, J., & Wang, K. (2018, February). Personalized top-n sequential recommendation via convolutional sequence embedding. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining (pp. 565-573).
[3] Kang, W. C., & McAuley, J. (2018, November). Self-attentive sequential recommendation. In 2018 IEEE International Conference on Data Mining (ICDM) (pp. 197-206). IEEE.
[4] Li, J., Wang, Y., & McAuley, J. (2020, January). Time interval aware self-attention for sequential recommendation. In Proceedings of the 13th international conference on web search and data mining (pp. 322-330).
[5] Yuan, F., Karatzoglou, A., Arapakis, I., Jose, J. M., & He, X. (2019, January). A simple convolutional generative network for next item recommendation. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining (pp. 582-590).
[6] Xu, C., Zhao, P., Liu, Y., Xu, J., S. Sheng, V. S. S., Cui, Z., ... & Xiong, H. (2019, May). Recurrent convolutional neural network for sequential recommendation. In The world wide web conference (pp. 3398-3404).
[7] Lin, J., Pan, W., & Ming, Z. (2020, September). FISSA: fusing item similarity models with self-attention networks for sequential recommendation. In Fourteenth ACM Conference on Recommender Systems (pp. 130-139).
[8] Li, Y., Chen, T., Zhang, P. F., & Yin, H. (2021, October). Lightweight self-attentive sequential recommendation. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management (pp. 967-977).
[9] Wu, J., Cai, R., & Wang, H. (2020, April). Déjà vu: A contextualized temporal attention mechanism for sequential recommendation. In Proceedings of The Web Conference 2020 (pp. 2199-2209).
[10] Wang, J., Liu, Q., Liu, Z., & Wu, S. (2019, November). Towards accurate and interpretable sequential prediction: A cnn & attention-based feature extractor. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management (pp. 1703-1712).
[11] Ji, W., Wang, K., Wang, X., Chen, T., & Cristea, A. (2020, October). Sequential recommender via time-aware attentive memory network. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management (pp. 565-574).
[12] Yu, F., Liu, Q., Wu, S., Wang, L., & Tan, T. (2016, July). A dynamic recurrent model for next basket recommendation. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval (pp. 729-732).
[13] Hidasi, B., Karatzoglou, A., Baltrunas, L., & Tikk, D. (2015). Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939. [14] Bai, T., Zou, L., Zhao, W. X., Du, P., Liu, W., Nie, J. Y., & Wen, J. R. (2019, July). Ctrec: A long-short demands evolution model for continuous-time recommendation. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 675-684).
[15] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.