請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66582
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 曹承礎(Seng-Cho Chou) | |
dc.contributor.author | Hsin-Hao Chen | en |
dc.contributor.author | 陳信豪 | zh_TW |
dc.date.accessioned | 2021-06-17T00:44:32Z | - |
dc.date.available | 2023-02-10 | |
dc.date.copyright | 2020-02-10 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2020-02-05 | |
dc.identifier.citation | Albert C. Bemmaor and Nicolas Glady. (2012) Modeling Purchasing
Behavior with Sudden “Death”: A Flexible Customer Lifetime Model. Management Science 58, 5, pp. 1012-1021. C. G. Brinton and M. Chiang. (2015) MOOC performance prediction via clickstream data and social learning networks, 2015 IEEE Conference on Computer Communications (INFOCOM), Kowloon, 2015, pp. 2299-2307. Cadez, Igor, David Heckerman, Christopher Meek, Padhraic Smyth. (2000) Visualization of navigation patterns on a Web site using model based clustering. Proc. Sixth ACM SIGKDD Internat. Conf. on Knowledge Discovery and Data Mining, Boston, MA, pp. 280-284. Cullinan G. J. (1977) Picking them by their batting averages: recency-frequency-monetary method of controlling circulation. Direct Mail/Marketing Association, New York, N.Y., USA. Manual Release 2103. David C. Schmittlein, Donald G. Morrison, and Richard Colombo. (1987) Counting Your Customers: Who Are They and What Will They Do Next? Management Science 33, 1, pp. 1-24. Donald G Morrison, David C Schmittlein, Source Journal, Royal Statistical, and Society Series. (1988) Generalizing the NBD model for Customer Purchases: What are the Implications and is it Worth the Effort? Journal of Business & Economic Statistics 6, 1, pp. 129-145. Hughes, Arthur. (2005) Strategic Database Marketing, 3rd ed. New York: McGraw-Hill. Peter S. Fader, Bruce G. S. Hardie, and Ka Lok Lee. (2005) Counting Your Customers? the Easy Way: An Alternative to the Pareto/NBD Model. Marketing Science 24, 2, pp. 275-284. Peter S. Fader, Bruce G. S. Hardie, and Ka Lok Lee. (2005) RFM and CLV: Using Iso-Value Curves for Customer Base Analysis. Journal of Marketing Research XLII, November, pp. 415-430. Sosa, Pedro M. (2017) Twitter Sentiment Analysis Using Combined LSTM-CNN Models. Bsides, konukoii.com/blog/2018/02/19/twitter-sentiment-analysis-using-combined-lstm-cnn-models Steven Tang, Joshua C. Peterson, Zachary A. Pardos. (2016) Deep Neural Networks and How They Apply to Sequential Education Data, Proceedings of the Third. ACM Conference on Learning @ Scale, April 25-26, 2016, Edinburgh, Scotland, UK Stone, Bob. (1994) Successful Direct Marketing Methods. Lincolnwood: NTC Business Books. Wendy W. Moe. (2003) Buying, Searching, or Browsing: Differentiating Between Online Shoppers Using In-Store Navigational Clickstream. Journal of Consumer Psychology. Volume 13, Issues 1-2, 2003, pp. 29-39. Yong Soo Kim, Bong-Jin Yum, Junehwa Song, Su Myeon Kim. (2005) Development of a recommender system based on navigational and behavioral patterns of customers in e-commerce sites. Expert Systems with Applications Volume 28, Issue 2, February 2005, pp. 381-393. Ypma A., Heskes T. (2003) Automatic Categorization of Web Pages and User Clustering with Mixtures of Hidden Markov Models. In: Zaïane O.R., Srivastava J., Spiliopoulou M., Masand B. (eds) WEBKDD 2002 - Mining Web Data for Discovering Usage Patterns and Profiles. WebKDD 2002. Lecture Notes in Computer Science, vol 2703. Springer, Berlin, Heidelberg. Zhenzhou Wu, Bao Hong Tan, Rubing Duan, Yong Liu, Rick Siow Mong Goh. (2015) Neural Modeling of Buying Behaviour for E-Commerce from Clicking Patterns, Proceedings of the 2015 International ACM Recommender Systems Challenge, p.1-4, September 16-20, 2015, Vienna, Austria. 任立中,陳靜怡 (2015),行銷研究-發展有效行銷策略之基石,前程文化事業有限公司,11月初版。 黃凱文 (2017),以數據驅動建立品牌,掌握長期營運趨 NAPL會員分析模型,會員活躍度分析指標,https://blog.91app.com/data-3/。 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66582 | - |
dc.description.abstract | 本研究之目的為通過點擊流數據分析電商顧客價值。我們首先應用海盜指標 (AARRR) 並將目標放在已活躍的顧客上,而後定義 Future Return 和 Future RFM 這兩項任務以協助我們進行價值衡量。在特徵工程中,我們將特徵分為五 大群,分別為 RFM 特徵群,CAI 特徵群,矩陣特徵群,偏好特徵群和其他特徵 群。其中特別的是,我們將行為視為某種價值信號,並藉此定義 Signal RFM 和 Signal CAI 作為技術指標來幫助電商快速有效地衡量顧客價值。我們訓練了邏輯 回歸 / 線性回歸、XGBoost、前饋神經網絡和 LSTM-CNN 模型來預測 Future Return 和 Future RFM。在實驗中,XGBoost 展現了其強大的效能和優秀的預測 能力,並被視為最佳單一模型。而 LSTM-CNN 通過採用最近顧客行為資料作為 模型附加輸入,顯示了其擊敗 XGBoost 的潛能。最後,我們再透過簡單的線性 回歸來集成學習所有單一模型的預測,並以此達到最佳結果。 | zh_TW |
dc.description.abstract | The purpose of this research is to analyze E-commerce customer value through clickstream data. At first, we apply AARRR model and focus on active customers. Then we define Future Return and Future RFM tasks to help us estimate the value of customer. For feature engineering, we generate five types of features: RFM, CAI, Matrix, Preference and Other. Especially, we consider behavior meaning as some kind of value signal and formulate Signal RFM and Signal CAI. These two technical indicators can help E-commerce companies measure customer value efficiently. Furthermore, we train Logistic / Linear Regression, XGBoost, Feed Forward Neural Network and LSTM-CNN models to predict Future Return and Future RFM. XGBoost has presented its outstanding performance and is considered to be the best single model for our tasks while LSTM-CNN shows the potential to beat XGBoost by adopting recent customer logs as additive model inputs. The ensemble of all the models by a simple Linear Regression model help us reach the best performance in the end. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T00:44:32Z (GMT). No. of bitstreams: 1 ntu-108-R06725048-1.pdf: 2901961 bytes, checksum: b490f9207db4adad1b596ad9fb229337 (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | CONTENTS
誌謝 I 中文摘要 II Abstract III CONTENTS IV LIST OF FIGURES VI LIST OF TABLES VIII Chapter 1 Introduction 1 1.1 Background 1 1.2 Objective 3 1.3 Scope 3 1.4 Research Process and Thesis Architecture 4 Chapter 2 Related Works 7 2.1 Customer Value 7 2.1.1 Buy ‘Til You Die 7 2.1.2 RFM 8 2.1.3 CAI 9 2.1.4 NAPL 10 2.1.5 AARRR 11 2.2 Clickstream Data 12 Chapter 3 Methodology 14 3.1 Dataset Description 14 3.2 Window Split 16 3.3 Train Test Split 17 3.4 Activation Threshold 18 3.5 Feature Engineering and Technical Indicator 19 3.5.1 RFM Features and Signal RFM 19 3.5.2 CAI Features and Signal CAI 21 3.5.3 Matrix Features 23 3.5.4 Preference Features 25 3.5.5 Other Features 28 3.6 Models 30 3.6.1 Logistic Regression and Linear Regression 30 3.6.2 XGBoost 32 3.6.3 Feed Forward Neural Network 34 3.6.4 LSTM-CNN 35 3.7 Ensemble 38 Chapter 4 Experiment Results 39 4.1 Feature Generation Days Comparison 39 4.2 Signal RFM and Signal CAI Effectiveness 41 4.3 Model Performance 42 4.4 Member vs. Visitor 43 Chapter 5 Conclusion 45 References 48 | |
dc.language.iso | en | |
dc.title | 運用點擊流之 Signal RFM 與 Signal CAI 分析顧客價值 | zh_TW |
dc.title | Analysis of Customer Value with Clickstream Based Signal RFM and Signal CAI | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-1 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 蔡益坤(Yih-Kuen Tsay) | |
dc.contributor.oralexamcommittee | 周子元 | |
dc.subject.keyword | 電子商務,顧客關係管理,顧客價值,點擊流,RFM,CAI,LSTM-CNN, | zh_TW |
dc.subject.keyword | E-commerce,Customer Relationship Management,Customer Value,Clickstream,RFM,CAI,LSTM-CNN, | en |
dc.relation.page | 50 | |
dc.identifier.doi | 10.6342/NTU201901840 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-02-06 | |
dc.contributor.author-college | 管理學院 | zh_TW |
dc.contributor.author-dept | 資訊管理學研究所 | zh_TW |
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-108-1.pdf 目前未授權公開取用 | 2.83 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。