本研究探討將長短期記憶神經網路應用於零售業之顧客回購機率預測。我們將原始銷售資料，轉換為包含RFM特徵的時間序列資料，提供神經網路模型學習顧客之行為特徵以進行預測，作為我們研究的主要核心；同時我們以隨機森林模型作為比較基礎，驗證了在有無進行特徵工程兩種不同條件下，長短期記憶神經網路為企業帶來的預測效果差異，並且通過統計檢定驗證模型之間差異是否顯著。最後在不同資料集測試在顧客回購週期與行為特徵不同的情況下，長短期記憶神經網路的通用性與效益。實驗結果顯示，特徵工程在長短期記憶神經網路訓練中仍有其必要性，在未進行特徵工程的情況下，長短期記憶神經網路在實驗中平均表現較隨機森林模型之Precision值低了0.14%，但在透過長短期記憶神經網路模型搭配RFM特徵學習的情況下，相較於透過隨機森林模型進行預測，平均Precision值提升了0.23%，這在統計意義上為顯著提升。

This study investigates the application of Long Short-Term Memory (LSTM) neural networks in predicting customer repurchase probability in the retail industry. We transformed raw sales data into time-series data with RFM (Recency, Frequency, Monetary) features, which serve as the core of our research by enabling the neural network to learn customer behavior patterns for prediction purposes. Simultaneously, we used a Random Forest model as a baseline for comparison, evaluating the predictive performance of LSTM with and without feature engineering. We also performed statistical tests to determine whether the differences between the models were significant. Finally, we tested the generalizability and effectiveness of the LSTM model across different datasets, considering variations in customer repurchase cycles and behavior characteristics. The experimental results demonstrate that feature engineering remains essential in LSTM training. Without feature engineering, the average Precision of the LSTM model in our experiments was 0.14% lower than that of the Random Forest model. However, when the LSTM model was trained with RFM features, the average Precision improved by 0.23% compared to the Random Forest model, which represents a statistically significant improvement.

吳奇廷.(2018). 應用機器學習於精準行銷之研究。 國立成功大學 會計系研究所碩士論文，台南市
吳育宏.(2014). 史上最成功的行銷案：花一億美元討好客戶的客戶, 商業周刊(https://www.businessweekly.com.tw/careers/blog/5908)
Agrawal, D., & Schorling, C. (1996). Market share forecasting: An empirical comparison of artificial neural networks and multinomial logit model. Journal of Retailing, 72(4), 383-407.
Bakir, H., Chniti, G., & Zaher, H. (2018). E-Commerce price forecasting using LSTM neural networks. International Journal of Machine Learning and Computing, 8(2), 169-174.
Chen, Y. L., Kuo, M. H., Wu, S. Y., & Tang, K. (2009). Discovering recency, frequency, and monetary (RFM) sequential patterns from customers’ purchasing data. Electronic Commerce Research and Applications, 8(5), 241-251.
Ding, G., & Qin, L. (2020). Study on the prediction of stock price based on the associated network model of LSTM. International Journal of Machine Learning and Cybernetics, 11(6), 1307-1317.
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European journal of operational research, 270(2), 654-669.
Glady, N., Baesens, B., & Croux, C. (2009). A modified Pareto/NBD approach for predicting customer lifetime value. Expert Systems with Applications, 36(2), 2062-2071.
Gomez-Uribe, C. A., & Hunt, N. (2015). The netflix recommender system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems (TMIS), 6(4), 1-19.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
Hsiao, B., Shu, L., & Hsieh, S. J. (2015, August). Predicting and testing probability of continuous purchasing of online customers. In 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) (pp. 783-788). IEEE.
Islam, M. T., Siddique, B. N. K., Rahman, S., & Jabid, T. (2018, October). Image recognition with deep learning. In 2018 International conference on intelligent informatics and biomedical sciences (ICIIBMS) (Vol. 3, pp. 106-110). IEEE.
Lauterborn, B. (1990). New marketing litany: four Ps passé: C-words take over.
Lee, H. I., Choi, I. Y., Moon, H. S., & Kim, J. K. (2020). A multi-period product recommender system in online food market based on recurrent neural networks. Sustainability, 12(3), 969.
Lopez, M. M., & Kalita, J. (2017). Deep Learning applied to NLP. arXiv preprint arXiv:1703.03091.
Ma, L., & Sun, B. (2020). Machine learning and AI in marketing–Connecting computing power to human insights. International Journal of Research in Marketing, 37(3), 481-504.
Mahesh, B. (2020). Machine learning algorithms-a review. International Journal of Science and Research (IJSR).[Internet], 9(1), 381-386.
Mesforoush, A., & Tarokh, M. J. (2013). Customer profitability segmentation for SMEs case study: network equipment company. International Journal of Research in Industrial Engineering, 2(1), 30-44.
Robin, A. L., & Covert, D. (2005). Does adjunctive glaucoma therapy affect adherence to the initial primary therapy?. Ophthalmology, 112(5), 863-868.
Sarkar, M., & De Bruyn, A. (2021). LSTM response models for direct marketing analytics: Replacing feature engineering with deep learning. Journal of Interactive Marketing, 53(1), 80-95.
Smith, W. R. (1956). Product differentiation and market segmentation as alternative marketing strategies. Journal of marketing, 21(1), 3-8.
Stormi, K., Lindholm, A., Laine, T., & Korhonen, T. (2020). RFM customer analysis for product-oriented services and service business development: an interventionist case study of two machinery manufacturers. Journal of Management and Governance, 24(3), 623-653.
Syawaludin, A., & Rintayati, P. (2019). Development of Augmented Reality-Based Interactive Multimedia to Improve Critical Thinking Skills in Science Learning. International Journal of Instruction, 12(4), 331-344.
Venugopal, V., & Baets, W. (1994). Neural networks & their applications in marketing management. Journal of Systems Management, 45(9), 16.
Wei, J. T., Lee, M. C., Chen, H. K., & Wu, H. H. (2013). Customer relationship management in the hairdressing industry: An application of data mining techniques. Expert Systems with Applications, 40(18), 7513-7518.
Wu, Z., Zang, C., Wu, C. H., Deng, Z., Shao, X., & Liu, W. (2021). Improving customer value index and consumption forecasts using a weighted RFM model and machine learning algorithms. Journal of Global Information Management (JGIM), 30(3), 1-23.
Yao, J., Teng, N., Poh, H. L., & Tan, C. L. (1998). Forecasting and analysis of marketing data using neural networks. J. Inf. Sci. Eng., 14(4), 843-862.
Zhu, G., & Gao, X. (2019). Precision retail marketing strategy based on digital marketing model. Science Journal of Business and Management, 7(1), 33-37.