簡易檢索 / 詳目顯示
| 研究生： |
吳英緩 Ying-Huan Wu |
|---|---|
| 論文名稱： |
運用機器學習演算法探討電商情境特徵和銷售表現對商品購物預測之影響 Exploring the effect of purchase prediction using contextual and sales performance features with machine learning algorithm in e-commerce |
| 指導教授： |
呂志豪
Shih-Hao Lu |
| 口試委員: |
曾盛恕
Seng-Su Tsang 陳崇文 Chung-Wen Chen |
| 學位類別： |
碩士 Master |
| 系所名稱： |
管理學院 - 企業管理系 Department of Business Administration |
| 論文出版年： | 2023 |
| 畢業學年度： | 111 |
| 語文別： | 英文 |
| 論文頁數： | 46 |
| 中文關鍵詞： | 購物意圖 、購買預測 、行銷分析 、機器學習 、電子商務 、極限梯度提升 |
| 外文關鍵詞： | Purchase Intention, Purchase Prediction, Marketing Analytics, Machine Learning, E-commerce, XGBoost |
| 相關次數： | 點閱：266 下載：27 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
近年來，線上購物的發展迅速成長且競爭激烈，而「提高商品購買轉換率(Conversion rate)」一直是電子商務公司的重要目標之一。為了達成這個目標，許多公司不僅持續追蹤與分析網站平台上的線上行為數據以更加了解客戶行為，更應用先進的機器學習技術優化使用者體驗並提升個人化行銷和推薦。
本研究使用拉丁美洲知名電商 — MercadoLibre 所提供的公開資料集，除了分析和探討與購物預測相關的重要特徵以外，亦運用機器學習模型驗證情境特徵和商品銷售表現對購買預測的影響。在探索性資料分析方面，本研究發現如果產品是在詳細資訊頁面上瀏覽，或是可以讓消費者即時追蹤其運輸狀態，可以獲得較高的商品轉換率。而在模型預測方面，本研究驗證加入商品銷售表現後所建構的機器學習模型可以有效提升預測準確率和其 F1 score。除此之外，隨機森林模型在購買預測方面的表現優於其他模型，由此實驗結果可得知新穎的機器學習模型並非總是能達到最好的效能。
本研究的貢獻在於提供和探討情境特徵和商品銷售表現對消費者購物意圖的影響，這些見解與分析可以改進電商公司的行銷策略，並通過更加準確的商品購物預測為線上消費者提供更加優質的用戶體驗。
Online shopping has been growing rapidly and competitively in recent years. One of the main goals of e-commerce companies is to increase the conversion rate of product purchases. To achieve this goal, lots of companies not only analyze customer data records on the website platform to learn more about customer behavior but also utilize advanced machine learning technologies to provide better user experience and personalized marketing and recommendation for their customer.
This paper analyzed important features related to predicting performance and investigate purchase prediction using contextual and sales performance features with machine learning models. Regarding data analysis, this study found that if the product was viewed on a detail information page or can be tracked in its shipping status timely, it could achieve higher CVR. On the other hand, ML models trained by both Contextual Features and Sales Performance Features could effectively improve predictive performances. Additionally, Random Forest performed the best in purchase prediction than other models.
The contribution of this paper is that explore the insights of Contextual Features and Sales Performance Features that can improve online marketing strategies and provide better user experience through personalized marketing and recommendation based on accurate purchase predictions.
Bader-El-Den, M., Teitei, E., & Perry, T. (2018). Biased random forest for dealing with the class imbalance problem. IEEE Transactions on Neural Networks and Learning Systems, 30(7), 2163–2172.
Chen, T. and Guestrin, C. (2016). XGBoost: A scalable tree boosting system. KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
Esmeli, R., Bader-El-Den, M., Abdullahi, H. (2022). An analyses of the effect of using contextual and loyalty features on early purchase prediction of shoppers in e-commerce domain. Journal of Business Research, 147, 420-434.
Esmeli,R., Bader-El-Den, M., & Abdullahi,H. (2021). Towards early purchase intention prediction in online session based retailing systems. Electronic Markets, 31, 697–715.
Feedvisor (2021) Feedvisor’s 2021 Amazon Consumer Behavior Report. Website: https://feedvisor.com/resources/amazon-marketing-advertising-strategies/2021-amazon-consumer-behavior-report/
Friedman, JH. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics. 29 (5), 1189 - 1232.
G. Ke , Q. Meng, T. Finley et al. (2017) ‘LightGBM: A highly efficient gradient boosting decision tree.’ Proceedings of the Advances in Neural Information Processing Systems, 2017, pp. 3146–3154.
Guan, M., Cha, M., Li, Y., Wang, Y., & Sun, J. (2020). From anticipation to action: Data reveal mobile shopping patterns during a yearly mega sale event in China. IEEE Transactions on Knowledge and Data Engineering.
Gupta, R., & Pathak, C. (2014). A machine learning framework for predicting purchase by online customers based on dynamic pricing. Procedia Computer Science, 36, 599–605.
Hallikainen, H., Savimäki, E., & Laukkanen, T. (2020). Fostering B2B sales with customer big data analytics. Industrial Marketing Management, 86, 90–98.
Hsu, C.-L., Yu, L.-C., & Chang, K.-C. (2017). Exploring the effects of online customer reviews, regulatory focus, and product type on purchase intention: Perceived justice as a moderator. Computers in Human Behavior, 69, 335–346.
Jannach, D., & Jugovac, M. (2019). Measuring the business value of recommender systems. ACM Transactions on Management Information Systems (TMIS), 10(4), 1–23.
Jannach, D., & Ludewig, M. (2017). When recurrent neural networks meet the neighborhood for session-based recommendation. In Proceedings of the eleventh ACM conference on recommender systems (pp. 306–310).
Jannach, D., Ludewig, M., & Lerche, L. (2017). Session-based item recommendation in e-commerce: on short-term intents, reminders, trends and discounts. User Modeling and User-Adapted Interaction, 27(3–5), 351–392.
Kim, E. Y., & Kim, Y.-K. (2004). Predicting online purchase intentions for clothing products. European Journal of Marketing.
Kim, E., Kim, W., & Lee, Y. (2003). Combination of multiple classifiers for the customer’s purchase behavior prediction. Decision Support Systems, 34(2), 167–175.
MercadoLibre (2019) Conversion Rate Prediction. Kaggle Website: https://www.kaggle.com/competitions/conversion-rate-prediction/overview
MercadoLibre (2020) Mercado Libre, Inc. Reports:First Quarter 2020 Financial Results: https://investor.mercadolibre.com/static-files/502aff41-fc86-4c47-b393-68d965d2682c
MercadoLibre (2022) About Mercado Libre. MercadoLibre Official Website: https://investor.mercadolibre.com/
MercadoLibre (2022) Mercado Libre Developer Open Platform: https://developers.mercadolibre.com.ar/en_us
Mokryn, O., Bogina, V., & Kuflik, T. (2019). Will this session end with a purchase? Inferring current purchase intent of anonymous visitors. Electronic Commerce Research and Applications, 34, Article 100836.
Nguyen, MH. (2019). Impacts of Unbalanced Test Data on the Evaluation of Classification Methods. International Journal of Advanced Computer Science and Applications. Vol. 10, No. 3.
Popovich, D., & Hamilton, R. (2020). Intermediate choice lists: How product attributes influence purchase likelihood in a self-imposed delay. Journal of Retailing.
Qiu, J., Lin, Z., & Li, Y. (2015). Predicting customer purchase behavior in the e-commerce context. Electronic Commerce Research, 15(4), 427–452.
Qiu, J., Lin, Z., & Li, Y. (2015). Predicting customer purchase behavior in the e-commerce context. Electronic Commerce Research, 15(4), 427–452.
Sakar, C. O., Polat, S. O., Katircioglu, M., & Kastro, Y. (2019). Real-time prediction of online shoppers’ purchasing intention using multilayer perceptron and LSTM recurrent neural networks. Neural Computing and Applications, 31(10), 6893–6908.
Salton, G., & McGill, M. (1983). Introduction to modern information retrieval. McGraw-Hill, NewYork, NY.
Sathya, R. and Abraham, A. (2013). Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification. International Journal of Advanced Research in Artificial Intelligence, 2, 34-38.
Zeng, M., Cao, H., Chen, M., & Li, Y. (2019). User behaviour modeling, recommendations, and purchase prediction during shopping festivals. Electronic Markets, 29(2), 263–274.
Zhao, Y., Yao, L., & Zhang, Y. (2016). Purchase prediction using Tmall-specific features. Concurrency Computations: Practice and Experience, 28(14), 3879–3894.
Zhu, G., Wu, Z., Wang, Y., Cao, S., & Cao, J. (2019). Online purchase decisions for tourism e-commerce. Electronic Commerce Research and Applications, 38, Article 100887.
Zhuang, L., Kou, Z., Zhang, C. (2005). Session identification based on time interval in web log mining. In IFIP Advances in information and communication technology, Vol. 163 pp. 389– 396.
