Purchase prediction on e-commerce platforms can help identify the likelihood of consumers completing a purchase after adding a product to the shopping cart. This study aims to evaluate the use of behavioral and temporal features to predict the purchase of the same product within 24 hours of add-to-cart activity by comparing the Logistic Regression and CatBoost algorithms. The study uses secondary data from the Synerise RecSys Challenge 2025 which includes product addition to cart activity and purchase activity. A total of 149,208 observations were used in modeling by dividing data based on time order into training, validation, and test data. The features used included the frequency of cart activity, user purchase history, time interval since previous activity or purchase, and temporal characteristics based on calendar. Model evaluation was conducted using ROC-AUC, Average Precision (AP), accuracy, precision, recall, and F1-score. The test results showed that CatBoost outperformed Logistic Regression on all six evaluation metrics, with a ROC-AUC of 0.6830, an AP of 0.4212, an accuracy of 0.6926, a precision of 0.3820, a recall of 0.5530, and an F1-score of 0.4518. A feature significance analysis showed that the number of users' historical purchases, the frequency of cart activity, and the time interval since the user's last purchase were the features that contributed the most to the prediction. In addition, the addition of customer identities and SKUs did not increase validation AP compared to the use of numerical features alone. The results showed that historical behavioral information has the potential to support short-term purchase predictions and that CatBoost provided better performance in the experiments conducted. However, testing on additional periods and datasets is still needed to assess the generalization capabilities and application of the model under real conditions.
Alamuri, O. R. S. G., & Bondalapu, C. K. (2026). Predicting e-commerce purchase intention using machine learning. ASEAN Journal of Scientific and Technological Reports, 29(1). https://doi.org/10.55164/ajstr.v29i1.260159
Bastos, J. A., & Bernardes, M. I. (2024). Understanding online purchases with explainable machine learning. Information, 15(10), Article 587. https://doi.org/10.3390/info15100587
Chopra, I. P., Jebarajakirthy, C., Jain, T., & Maseeh, H. I. (2024). Electronic shopping cart abandonment: What do we know and where should we be heading? Electronic Markets, 34, Article 25. https://doi.org/10.1007/s12525-024-00697-0
Kafilla, P. I., Utomo, F. S., & Karyono, G. (2025). Enhancing customer purchase behavior prediction using PSO-tuned ensemble machine learning models. Journal of Informatics Engineering (JUTIF), 6(5), 3509–3525. https://doi.org/10.52436/1.jutif.2025.6.5.4952
Mishra, L. N., Rangari, A., Nagrare, S., & Nayak, S. K. (2026). A taxonomy for detecting and preventing temporal data leakage in machine learning-based build prediction: A dual-platform empirical validation. PLOS ONE, 21(5), Article e0340167. https://doi.org/10.1371/journal.pone.0340167
Wen, Z., Lin, W., & Liu, H. (2023). Machine-learning-based approach for anonymous online customer purchase intentions using clickstream data. Systems, 11(5), Article 255. https://doi.org/10.3390/systems11050255
Apicella, A., Isgrò, F., & Prevete, R. (2025). Don’t push the button! Exploring data leakage risks in machine learning and transfer learning. Artificial Intelligence Review, 58, Article 339. https://doi.org/10.1007/s10462-025-11326-3
Ruan, W., & Zhai, Z. (2026). Predicting user purchase behavior via multidimensional feature engineering and explainable machine learning. Journal of Theoretical and Applied Electronic Commerce Research, 21(10), Article 352. https://doi.org/10.3390/jtaer21100352
Sujon, K. M., Hassan, R., Choi, K., & Samad, M. A. (2025). Accuracy, precision, recall, f1-score, or MCC? Empirical evidence from advanced statistics, ML, and XAI for evaluating business predictive models. Journal of Big Data, 12, Article 268. https://doi.org/10.1186/s40537-025-01313-4
Suo, L., Xia, L., Chung, Y., & Kim, E. (2026). Layered feature engineering for e-commerce purchase prediction: A hierarchical evaluation on Taobao user behavior datasets. Computers, Materials & Continua, 87(1), Article 78. https://doi.org/10.32604/cmc.2025.076329
Abdullah-All-Tanvir, Khandokar, I. A., Islam, A. K. M. M., Islam, S., & Shatabda, S. (2023). A gradient boosting classifier for purchase intention prediction of online shoppers. Heliyon, 9(4), e15163. https://doi.org/10.1016/j.heliyon.2023.e15163
Zhou, S., & Hudin, N. S. (2024). Advancing e-commerce user purchase prediction: Integration of time-series attention with event-based timestamp encoding and graph neural network-enhanced user profiling. PLOS ONE, 19(4), e0299087. https://doi.org/10.1371/journal.pone.0299087
Baati, K., & Mohsil, M. (2020). Real-time prediction of online shoppers’ purchasing intention using random forest. In I. Maglogiannis, L. Iliadis, & E. Pimenidis (Eds.), Artificial intelligence applications and innovations (Vol. 583, pp. 43–51). Springer. https://doi.org/10.1007/978-3-030-49161-1_4
Chen, Y., Liu, H., Wen, Z., & Lin, W. (2023). How explainable machine learning enhances intelligence in explaining consumer purchase behavior: A random forest model with anchoring effects. Systems, 11(6), Article 312. https://doi.org/10.3390/systems11060312
Lin, J. (2025). Application of machine learning in predicting consumer behavior and precision marketing. PLOS ONE, 20(5), Article e0321854. https://doi.org/10.1371/journal.pone.0321854
Requena, B., Cassani, G., Tagliabue, J., Greco, C., & Lacasa, L. (2020). Shopper intent prediction from clickstream e-commerce data with minimal browsing information. Scientific Reports, 10, Article 16983. https://doi.org/10.1038/s41598-020-73622-y
Wang, W., Xiong, W., Wang, J., Tao, L., Li, S., Yi, Y., Zou, X., & Li, C. (2023). A user purchase behavior prediction method based on XGBoost. Electronics, 12(9), Article 2047. https://doi.org/10.3390/electronics12092047
Yang, Y. (2025). Data-driven prediction of future purchase behavior in cross-border e-commerce using sequence modeling with PSO-tuned LSTM. PLOS ONE, 20(12), Article e0337932. https://doi.org/10.1371/journal.pone.0337932