請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96191完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 盧信銘 | zh_TW |
| dc.contributor.advisor | Hsin-Min Lu | en |
| dc.contributor.author | 李懿恩 | zh_TW |
| dc.contributor.author | I-En Lee | en |
| dc.date.accessioned | 2024-11-28T16:06:26Z | - |
| dc.date.available | 2025-10-01 | - |
| dc.date.copyright | 2024-11-28 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-09-10 | - |
| dc.identifier.citation | Arora, S., Liang, Y., & Ma, T. (2022, July 21). A Simple but Tough-to-Beat Baseline for Sentence Embeddings. International Conference on Learning Representations. https://openreview.net/forum?id=SyK00v5xx
Barkan, O., & Koenigstein, N. (2016). ITEM2VEC: Neural item embedding for collaborative filtering. 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 1–6. https://doi.org/10.1109/MLSP.2016.7738886 Bengio, Y., Ducharme, R., Vincent, P., & Jauvin, C. (2003). A Neural Probabilistic Language Model. Journal of Machine Learning Research, 3(Feb), 1137–1155. Bi, X., Adomavicius, G., Li, W., & Qu, A. (2022). Improving Sales Forecasting Accuracy: A Tensor Factorization Approach with Demand Awareness. INFORMS Journal on Computing, 34(3), 1644–1660. https://doi.org/10.1287/ijoc.2021.1147 Bianchi, F., Yu, B., & Tagliabue, J. (2021). BERT Goes Shopping: Comparing Distributional Models for Product Representations. In S. Malmasi, S. Kallumadi, N. Ueffing, O. Rokhlenko, E. Agichtein, & I. Guy (Eds.), Proceedings of the 4th Workshop on e-Commerce and NLP (pp. 1–12). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.ecnlp-1.1 Biś, D., Podkorytov, M., & Liu, X. (2021). Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications. In K. Toutanova, A. Rumshisky, L. Zettlemoyer, D. Hakkani-Tur, I. Beltagy, S. Bethard, R. Cotterell, T. Chakraborty, & Y. Zhou (Eds.), Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 5117–5130). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.naacl-main.403 Blei, D. M., Ng, A. Y., Jordan, M. I., & Lafferty, J. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3(4/5), 993–1022. Chen, F., Liu, X., Proserpio, D., Troncoso, I., & Xiong, F. (2020a). Studying Product Competition Using Representation Learning. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 1261–1268. https://doi.org/10.1145/3397271.3401041 Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020b). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the 37th International Conference on Machine Learning, 1597–1607. https://proceedings.mlr.press/v119/chen20j.html Chen, X., Zhang, C., Zhao, X.-L., Saunier, N., & Sun, L. (2022). Nonstationary Temporal Matrix Factorization for Multivariate Time Series Forecasting. arXiv preprint arXiv:2203.10651. https://doi.org/10.48550/arXiv.2203.10651 Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In J. Burstein, C. Doran, & T. Solorio (Eds.), Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) (pp. 4171–4186). Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423 Ding, H., Ma, Y., Deoras, A., Wang, Y., & Wang, H. (2021). Zero-Shot Recommender Systems. arXiv preprint arXiv:2105.08318. https://doi.org/10.48550/arXiv.2105.08318 Ethayarajh, K. (2019). How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings. In K. Inui, J. Jiang, V. Ng, & X. Wan (Eds.), Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (pp. 55–65). Association for Computational Linguistics. https://doi.org/10.18653/v1/D19-1006 Gabel, S., Guhl, D., & Klapper, D. (2019). P2V-MAP: Mapping Market Structures for Large Retail Assortments. Journal of Marketing Research, 56(4), 557–580. https://doi.org/10.1177/0022243719833631 Gabel, S., & Timoshenko, A. (2021). Product Choice with Large Assortments: A Scalable Deep-Learning Model. Management Science. https://doi.org/10.1287/mnsc.2021.3969 Gao, J., He, D., Tan, X., Qin, T., Wang, L., & Liu, T. (2018, September 27). Representation Degeneration Problem in Training Natural Language Generation Models. International Conference on Learning Representations. https://openreview.net/forum?id=SkEYojRqtm Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. In M.-F. Moens, X. Huang, L. Specia, & S. W. Yih (Eds.), Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (pp. 6894–6910). Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.emnlp-main.552 Grbovic, M., Radosavljevic, V., Djuric, N., Bhamidipati, N., Savla, J., Bhagwan, V., & Sharp, D. (2015). E-commerce in Your Inbox: Product Recommendations at Scale. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1809–1818. https://doi.org/10.1145/2783258.2788627 Harris, Z. S. (1954). Distributional Structure. WORD, 10(2–3), 146–162. https://doi.org/10.1080/00437956.1954.11659520 Hinton, G. E., McClelland, J. L., & Rumelhart, D. E. (1986). Distributed representations. In Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1: Foundations (pp. 77–109). MIT Press. Hou, Y., He, Z., McAuley, J., & Zhao, W. X. (2023). Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders. Proceedings of the ACM Web Conference 2023, 1162–1171. https://doi.org/10.1145/3543507.3583434 Hou, Y., Mu, S., Zhao, W. X., Li, Y., Ding, B., & Wen, J.-R. (2022). Towards Universal Sequence Representation Learning for Recommender Systems. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 585–593. https://doi.org/10.1145/3534678.3539381 Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix Factorization Techniques for Recommender Systems. Computer, 42(8), 30–37. Computer. https://doi.org/10.1109/MC.2009.263 Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2020). ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. arXiv preprint arXiv:1909.11942. https://doi.org/10.48550/arXiv.1909.11942 Levy, O., & Goldberg, Y. (2014). Neural Word Embedding as Implicit Matrix Factorization. Advances in Neural Information Processing Systems, 27. https://proceedings.neurips.cc/paper/2014/hash/feab05aa91085b7a8012516bc3533958-Abstract.html Li, B., Zhou, H., He, J., Wang, M., Yang, Y., & Li, L. (2020). On the Sentence Embeddings from Pre-trained Language Models. In B. Webber, T. Cohn, Y. He, & Y. Liu (Eds.), Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 9119–9130). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.733 Liang, M., Yang, L., Li, K., & Zhai, H. (2024). Improved collaborative filtering for cross-store demand forecasting. Computers & Industrial Engineering, 190, 110067. https://doi.org/10.1016/j.cie.2024.110067 Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692. https://doi.org/10.48550/arXiv.1907.11692 McAuley, J., Pandey, R., & Leskovec, J. (2015). Inferring Networks of Substitutable and Complementary Products. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2783258.2783381 Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013a). Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:1301.3781. https://doi.org/10.48550/arXiv.1301.3781 Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013b). Distributed Representations of Words and Phrases and their Compositionality. Advances in Neural Information Processing Systems, 26. https://papers.nips.cc/paper_files/paper/2013/hash/9aa42b31882ec039965f3c4923ce901b-Abstract.html Mimno, D., & Thompson, L. (2017). The strange geometry of skip-gram with negative sampling. Empirical Methods in Natural Language Processing. https://par.nsf.gov/biblio/10057832-strange-geometry-skip-gram-negative-sampling Mu, J., & Viswanath, P. (2018, February 15). All-but-the-Top: Simple and Effective Postprocessing for Word Representations. International Conference on Learning Representations. https://openreview.net/forum?id=HkuGJ3kCb Oord, A. van den, Li, Y., & Vinyals, O. (2019). Representation Learning with Contrastive Predictive Coding. arXiv preprint arXiv:1807.03748. https://doi.org/10.48550/arXiv.1807.03748 Raziperchikolaei, R., Liang, G., & Chung, Y. (2021). Shared Neural Item Representations for Completely Cold Start Problem. Proceedings of the 15th ACM Conference on Recommender Systems, 422–431. https://doi.org/10.1145/3460231.3474228 Ruiz, F. J. R., Athey, S., & Blei, D. M. (2020). SHOPPER: A probabilistic model of consumer choice with substitutes and complements. The Annals of Applied Statistics, 14(1), 1–27. https://doi.org/10.1214/19-AOAS1265 Shocker, A. D., Bayus, B. L., & Kim, N. (2004). Product Complements and Substitutes in the Real World: The Relevance of “Other Products.” Journal of Marketing, 68(1), 28–40. https://doi.org/10.1509/jmkg.68.1.28.24032 Sun, F., Liu, J., Wu, J., Pei, C., Lin, X., Ou, W., & Jiang, P. (2019). BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 1441–1450. https://doi.org/10.1145/3357384.3357895 Tkachuk, S., Wróblewska, A., Dabrowski, J., & Łukasik, S. (2022). Identifying Substitute and Complementary Products for Assortment Optimization with Cleora Embeddings. 2022 International Joint Conference on Neural Networks (IJCNN), 1–7. https://doi.org/10.1109/IJCNN55064.2022.9892361 Wang, L., Huang, J., Huang, K., Hu, Z., Wang, G., & Gu, Q. (2019, September 25). Improving Neural Language Generation with Spectrum Control. International Conference on Learning Representations. https://openreview.net/forum?id=ByxY8CNtvr Wang, T., & Isola, P. (2020). Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere. Proceedings of the 37th International Conference on Machine Learning, 9929–9939. https://proceedings.mlr.press/v119/wang20k.html Wang, Z., Jiang, Z., Ren, Z., Tang, J., & Yin, D. (2018). A Path-constrained Framework for Discriminating Substitutable and Complementary Products in E-commerce. Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, 619–627. https://doi.org/10.1145/3159652.3159710 Xie, R., Qiu, Z., Zhang, B., & Lin, L. (2023). Multi-granularity Item-Based Contrastive Recommendation. In X. Wang, M. L. Sapino, W.-S. Han, A. El Abbadi, G. Dobbie, Z. Feng, Y. Shao, & H. Yin (Eds.), Database Systems for Advanced Applications (pp. 406–416). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-30672-3_27 Xu, D., Ruan, C., Korpeoglu, E., Kumar, S., & Achan, K. (2020). Product Knowledge Graph Embedding for E-commerce. Proceedings of the 13th International Conference on Web Search and Data Mining, 672–680. https://doi.org/10.1145/3336191.3371778 Yang, J., Yi, X., Zhiyuan Cheng, D., Hong, L., Li, Y., Xiaoming Wang, S., Xu, T., & Chi, E. H. (2020). Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations. Companion Proceedings of the Web Conference 2020, 441–447. https://doi.org/10.1145/3366424.3386195 Yao, T., Yi, X., Cheng, D. Z., Yu, F., Chen, T., Menon, A., Hong, L., Chi, E. H., Tjoa, S., Kang, J. (Jay), & Ettinger, E. (2021). Self-supervised Learning for Large-scale Item Recommendations. Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 4321–4330. https://doi.org/10.1145/3459637.3481952 Zhao, K., Li, Y., Shuai, Z., & Yang, C. (2018). Learning and Transferring IDs Representation in E-commerce. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 1031–1039. https://doi.org/10.1145/3219819.3219855 | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96191 | - |
| dc.description.abstract | 產品關係是零售商在制定決策時的重要依據，透過分析產品關係，零售商能夠識別競爭產品、優化產品陳列、並制定綑綁銷售和促銷策略，從而提升效益與收入。然而，傳統零售商通常僅擁有有限的交易資料，獲取額外外部數據往往需要高昂的成本。在這種缺乏豐富產品資訊的情境下，準確分析產品關係成為一項挑戰。此外，由於產品更新迅速，新品不斷湧現，進一步增加了分析的難度。隨著多通路行銷與全通路行銷策略的興起，多商店的情境逐漸增加，分析中必須考量不同商店間的差異。
受到自然語言處理領域語言模型成功應用於電子商務的啟發，本研究採用Word2Vec框架，結合商店資訊，從多商店的電子發票資料集中捕捉產品共現關係(Co-occurrence)，進而學習低維度的產品與商店表徵。我們還設計了兩種利用產品名稱進行表徵編碼的模型，包括從頭訓練(Training from Scratch)的模型與基於BERT編碼的模型，以解決新產品的問題。 我們通過三項真實世界任務來評估所學表徵的性能：(1)識別替代品與互補品；(2)將個體層級的產品關係遷移至聚合層級的缺失銷售資料預測；(3)多商店的產品配對推薦。實驗結果顯示，僅利用產品ID產生表徵的簡單模型在三項任務中均表現優於其他模型。此外，我們的模型展現了將個體層級的產品關係遷移至聚合層級的缺失銷售預測的潛力。進一步分析顯示，使用產品名稱進行編碼的模型表現不佳的原因在於其表徵呈現各向異性分布(Anisotropic Distribution)，降低了表徵的表達性，且模型未能充分捕捉產品間的關係。未來，我們計畫針對這些問題改進模型架構，並將預訓練的表徵與時間序列方法相結合，以提升銷售預測的準確性及適應真實世界情境的能力。 | zh_TW |
| dc.description.abstract | Product relationships are crucial for retailers when making marketing decisions, as analyzing these relationships can help identify competitors, optimize product display, and design bundling and promotional strategies, enhancing profitability and revenue. However, traditional retailers often rely on limited transaction data, and obtaining external data can be costly, making analyzing product relationships become a challenge. Furthermore, the rapid turnover of products and the frequent introduction of new products complicate the analysis even more. With the rise of multichannel and omnichannel marketing strategies, the multi-store scenario is expected to grow. Store heterogeneity may not be ignored in the analysis.
Inspired by the success of language models in natural language processing applied to e-commerce, this study leverages the Word2Vec framework to integrate store information and capture product co-occurrence relationships from a multi-store e-invoice dataset, enabling the learning of low-dimensional representations of products and stores. We also developed two models that encode product names into product representations: a model trained from scratch and a BERT-based encoding model, designed to address the challenges of unseen products. We evaluate the learned representations across three real-world tasks: (1) identifying substitutes and complements, (2) transferring from individual-level relationship to aggregate-level missing sales prediction, and (3) multi-store matching recommendation. The experimental results show that the simple model, which generates product representations solely from product IDs, outperforms other models across all three tasks. Additionally, our model demonstrates potential in transferring individual-level product relationships to aggregate-level missing sales prediction. Further analysis reveals that the models using product name encoding underperform due to anisotropic distribution of representations, which reduce their expressiveness and hindered the capture of product relationships. In the future, we aim to address these issues by refining the approach and integrating our pre-trained representations with time-series methods to enhance sales prediction accuracy and better adapt to real-world scenarios. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-11-28T16:06:26Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-11-28T16:06:26Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 i
中文摘要 ii ABSTRACT iii TABLE OF CONTENTS v LIST OF FIGURES viii LIST OF TABLES ix Chapter 1 Introduction 1 Chapter 2 Literature Review 6 2.1 Identifying Substitutes and Complements 6 2.2 Distributed Representation 8 2.2.1 Word2Vec 9 2.2.2 Bidirectional Encoder Representations from Transformers (BERT) 10 2.3 Representation Learning in E-Commerce 11 2.3.1 Matrix Factorization 11 2.3.2 Two-tower Model 12 2.3.3 Leveraging Language Model Framework 14 2.3.3.1 Applying Word2Vec 14 2.3.3.2 Applying BERT 16 2.3.4 Summary for Representation Learning in E-Commerce 18 2.4 Embeddings Analysis in NLP 18 2.4.1 Word2Vec Analysis 19 2.4.2 BERT Analysis 19 2.5 Research Gap and Research Question 20 Chapter 3 Methodology 22 3.1 Overview 22 3.2 Data Preparation 24 3.2.1 Data Source 24 3.2.2 Data Preprocessing 24 3.3 Model 25 3.3.1 Product ID Skip-gram Model (ID-SG) 26 3.3.2 Term-level Skip-gram Model (Term-SG) 27 3.3.3 Skip-gram Model with BERT (BERT-SG) 30 3.4 Model Learning 34 Chapter 4 Experiments 36 4.1 Identification of Complements and Substitutes 36 4.1.1 Task Setup 36 4.1.2 Evaluation Metrics 37 4.2 Transferring from Individual-Level Relationship to Aggregate-Level Missing Sales Prediction Task 38 4.2.1 Task Setup 39 4.2.2 Evaluation Metrics 40 4.2.3 Model Comparison 41 4.3 Multi-store Matching Recommendation Task 42 4.3.1 Task Setup 42 4.3.2 Evaluation Metrics 43 4.3.3 Model Comparison 44 4.4 Results 44 Chapter 5 Analysis and Discussion 48 5.1 Geometry of Product Embeddings 48 5.2 Why Does the Models Using Textual Representation Not Work? 55 5.2.1 Term-SG Model 55 5.2.2 BERT-SG Model 56 Chapter 6 Conclusion 58 REFERENCE 59 APPENDIX 67 | - |
| dc.language.iso | en | - |
| dc.subject | 表徵學習 | zh_TW |
| dc.subject | BERT | zh_TW |
| dc.subject | 類神經網路 | zh_TW |
| dc.subject | 自然語言處理 | zh_TW |
| dc.subject | 電子發票 | zh_TW |
| dc.subject | Word2Vec | zh_TW |
| dc.subject | Neural Networks | en |
| dc.subject | Natural Language Processing | en |
| dc.subject | E-invoice | en |
| dc.subject | Representation Learning | en |
| dc.subject | BERT | en |
| dc.subject | Word2Vec | en |
| dc.title | 利用多商店的電子發票交易資料探討產品關係的表徵學習及其應用 | zh_TW |
| dc.title | Learning Product Representation in Multi-store E-invoice Transaction Data for Product Relationship Understanding and Its Applications | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-1 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 簡宇泰;柯士文 | zh_TW |
| dc.contributor.oralexamcommittee | Yu-Tai Chien;Shih-Wen Ke | en |
| dc.subject.keyword | 表徵學習,電子發票,自然語言處理,類神經網路,Word2Vec,BERT, | zh_TW |
| dc.subject.keyword | Representation Learning,E-invoice,Natural Language Processing,Neural Networks,Word2Vec,BERT, | en |
| dc.relation.page | 84 | - |
| dc.identifier.doi | 10.6342/NTU202404359 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-09-10 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-1.pdf 未授權公開取用 | 2.3 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。