Predicting E-Commerce Purchase Intention from Web Session Behavior: Feature Engineering, Imbalanced Learning, and Conversion Decision Support E-Commerce Purchase Intention Prediction
Main Article Content
Keywords
e-commerce purchase intention, web session behavior, feature engineering, imbalanced learning, conversion decision support
Abstract
Online purchase intention prediction is valuable for e-commerce operations, but the positive purchase class is rare and purely accuracy-oriented models can mislead conversion decisions. This paper studies a reproducible decision-support pipeline, FIDDS, for session-level purchase prediction from web behavior. FIDDS combines behavior-driven interaction features, imbalance-aware learning, probability calibration, and utility-based threshold selection. Experiments use the real UCI Online Shoppers Purchasing Intention Dataset with 12,330 sessions, 1,908 purchase sessions, and five stratified random seeds. Random Forest achieves the highest PR-AUC at 0.7453, while FIDDS achieves PR-AUC 0.7426, ROC-AUC 0.9301, F1 0.5723, recall 0.9173, lift at the top 10% of sessions 5.0233, and expected utility 0.1321. The results indicate that conversion-oriented evaluation changes how a model should be selected: the strongest classifier is not always the clearest operating policy. The evidence is limited to one public benchmark and should be read as decision-support validation rather than proof of platform-wide causal uplift.
References
- [1]Douglas Cirqueira, Markus Hofer, Dietmar Nedbal, Markus Helfert, and Marija Bezbradica. 2020. Customer Purchase Behavior Prediction in E-commerce: A Conceptual Framework and Research Agenda. In New Frontiers in Mining Complex Patterns. Lecture Notes in Computer Science, Vol. 11948. Springer, 119-136. https://doi.org/10.1007/978-3-030-48861-1_8.
- [2]Mariya Hendriksen, Ernst Kuiper, Pim Nauts, Sebastian Schelter, and Maarten de Rijke. 2020. Analyzing and Predicting Purchase Intent in E-commerce: Anonymous vs. Identified Customers. In The 2020 SIGIR Workshop on eCommerce. Article 23, 10 pages. https://sigir-ecom.github.io/ecom20Papers/paper23.pdf.
- [3]Qi Jiang. 2025. Purchase Intention Analysis of Online Shoppers Based on Machine Learning and K-Means Clustering. In Proceedings of the 2nd International Conference on Data Science and Engineering. SciTePress, 259-264. https://doi.org/10.5220/0013686100004670.
- [4]Md. Shahriare Satu and Syed Faridul Islam. 2023. Modeling Online Customer Purchase Intention Behavior Applying Different Feature Engineering and Classification Techniques. Discover Artificial Intelligence 3 (2023), Article 36. https://doi.org/10.1007/s44163-023-00086-0.
- [5]Nitesh V. Chawla, Kevin W. Bowyer, Lawrence O. Hall, and W. Philip Kegelmeyer. 2002. SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research 16 (2002), 321-357.
- [6]Haibo He and Edwardo A. Garcia. 2009. Learning from Imbalanced Data. IEEE Transactions on Knowledge and Data Engineering 21, 9 (2009), 1263-1284. https://doi.org/10.1109/TKDE.2008.239.
- [7]Orieb Abu Alghanam, Sumaya N. Al-Khatib, and Mohammad O. Hiari. 2022. Data Mining Model for Predicting Customer Purchase Behavior in E-Commerce Context. International Journal of Advanced Computer Science and Applications 13, 2 (2022), 421-428. https://doi.org/10.14569/IJACSA.2022.0130249.
- [8]Netci Hesvindrati, Afrig Aminuddin, Jhingga Mahadhni, Agung Pambudi, and Bambang Sudaryatno. 2025. Behavior-Based Purchase Intent Prediction in E-Commerce: A Machine Learning Approach. International Journal of Current Science Research and Review 8, 8 (2025), 3970-3980. https://doi.org/10.5281/zenodo.16734788.
- [9]Farisha Irwayu, Lintang Yuniar Banowosari, and Karmilasari. 2024. Implementation of Random Forest in Online Shoppers Purchasing Intention Analysis. International Research Journal of Advanced Engineering and Science 9, 1 (2024), 23-29.
- [10]Yumeng Wang and Chenwei Zhang. 2023. Research on Customer Purchase Intention Prediction Methods for E-Commerce Platforms Based on User Behavior Data. Journal of Advanced Computing Systems 3, 10 (2023), 23-38. https://doi.org/10.69987/JACS.2023.31003.
- [11]C. Okan Sakar, S. Olcay Polat, Mete Katircioglu, and Yomi Kastro. 2019. Real-time prediction of online shoppers' purchasing intention using multilayer perceptron and LSTM recurrent neural networks. Neural Computing and Applications 31, 10 (2019), 6893-6908. https://doi.org/10.1007/s00521-018-3523-0.
- [12]Leo Breiman. 2001. Random Forests. Machine Learning 45 (2001), 5-32. https://doi.org/10.1023/A:1010933404324.
- [13]Jesse Davis and Mark Goadrich. 2006. The Relationship Between Precision-Recall and ROC Curves. In Proceedings of the 23rd International Conference on Machine Learning. 233-240. https://doi.org/10.1145/1143844.1143874.
- [14]Bianca Zadrozny and Charles Elkan. 2002. Transforming Classifier Scores into Accurate Multiclass Probability Estimates. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 694-699. https://doi.org/10.1145/775047.775151.
- [15]Fabian Pedregosa, Gael Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake VanderPlas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and Edouard Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825-2830.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.