Bi-LSTM with Explainable AI for Session Duration-Based Customer Lifetime Value Proxy on Multi-Category E-Commerce Platforms
DOI:
https://doi.org/10.30871/jaic.v9i6.11578Keywords:
Bi-LSTM, Customer Lifetime Value, E-Commerce Multi-Category, Explainable Artificial Intelligence, User Session DurationAbstract
The rapid growth of multi-category e-commerce platforms has increased the importance of behavioral data for predicting Customer Lifetime Value (CLV). However, monetary-based CLV estimation is often infeasible due to incomplete or unavailable transaction records. This study adopts session duration as a short-term behavioral proxy for CLV and proposes a Bidirectional Long Short-Term Memory (Bi-LSTM) model enhanced with a Temporal Attention mechanism to improve predictive accuracy. The publicly available REES46 dataset, consisting of 1,6 million events and 276.000 unique sessions, is used with preprocessing steps including label encoding, temporal feature construction, and outlier-aware sampling to address the highly right-skewed distribution of session durations. Four baseline models Decision Tree, Random Forest, Extreme Gradient Boosting (XGBoost), and conventional Long Short-Term Memory (LSTM) are implemented for comparative evaluation. The baseline LSTM achieves MAE = 0,0080 and RMSE = 0,0322. The proposed Bi-LSTM v3 model, equipped with Temporal Attention and structured sampling, demonstrates substantial performance improvement, achieving MAE = 0,0043 (≈368 seconds) and RMSE = 0,0172 (≈1466 seconds), representing an accuracy gain of approximately 45–50% over the baseline. Explainability analysis using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) confirms that the time_diff feature is the dominant contributor at both global and local levels, aligning with the behavior of the attention mechanism. Additionally, the integration of Explainable Artificial Intelligence (XAI) provides transparent insights into model decision patterns. These findings show that combining Bi-LSTM, Temporal Attention, and XAI yields an accurate and interpretable framework for session duration prediction, supporting the use of session duration as a feasible CLV proxy in multi-category e-commerce environments.
Downloads
References
[1] E. B. Firmansyah, M. R. Machado, and J. L. R. Moreira, “How can Artificial Intelligence (AI) be used to manage Customer Lifetime Value (CLV)—A systematic literature review,” Int. J. Inf. Manag. Data Insights, vol. 4, no. 2, p. 100279, Nov. 2024, doi: 10.1016/j.jjimei.2024.100279.
[2] D. Egorenkov, “AI-Powered Predictive Customer Lifetime Value: Maximizing Long-Term Profits,” Int. J. Sci. Res. Manag., vol. 12, no. 09, pp. 7339–7354, 2024, doi: 10.18535/ijsrm/v12i09.em02.
[3] S. Adamu, A. Iorliam, and Ö. Asilkan, “Exploring Explainability in Multi-Category Electronic Markets: A Comparison of Machine Learning and Deep Learning Approaches,” J. Futur. Artif. Intell. Technol., vol. 1, no. 4, pp. 440–454, Mar. 2025, doi: 10.62411/faith.3048-3719-58.
[4] G. Yılmaz Benk, B. Badur, and S. Mardikyan, “A New 360° Framework to Predict Customer Lifetime Value for Multi-Category E-Commerce Companies Using a Multi-Output Deep Neural Network and Explainable Artificial Intelligence,” Inf., vol. 13, no. 8, 2022, doi: 10.3390/info13080373.
[5] J. Bauer and D. Jannach, “Improved Customer Lifetime Value Prediction with Sequence-To-Sequence Learning and Feature-Based Models,” ACM Trans. Knowl. Discov. Data, vol. 15, no. 5, 2021, doi: 10.1145/3441444.
[6] D. Kvíčala, M. Králová, and P. Suchánek, “The impact of online purchase behaviour on customer lifetime value,” J. Mark. Anal., no. 2000, 2024, doi: 10.1057/s41270-024-00328-9.
[7] A. A. TOKUÇ and T. Dag, “Predicting User Purchases From Clickstream Data : A Comparative Analysis of Clickstream Data Representations and Machine Learning Models,” vol. 13, no. March, 2025, doi: 10.1109/ACCESS.2025.3548267.
[8] A. Prashanthan, “An Integrated Framework for Optimizing Customer Retention Budget using Clustering, Classification, and Mathematical Optimization,” J. Comput. Theor. Appl., vol. 3, no. 1, pp. 45–63, 2025, doi: 10.62411/jcta.13194.
[9] V. Sakalauskas and D. Kriksciuniene, “Personalized Advertising in E-Commerce: Using Clickstream Data to Target High-Value Customers,” Algorithms, vol. 17, no. 1, 2024, doi: 10.3390/a17010027.
[10] W. Ullah, A. Ullah, I. U. Haq, K. Muhammad, M. Sajjad, and S. W. Baik, “CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks,” Multimed. Tools Appl., vol. 80, no. 11, pp. 16979–16995, 2021, doi: 10.1007/s11042-020-09406-3.
[11] D. Anitha Kumari, M. Shuaib Siddiqui, R. Dorbala, R. Megala, K. T. Vigneswara Rao, and N. Srikanth Reddy, “Deep Learning Models for Customer Lifetime Value Prediction in E-commerce,” in 2024 5th International Conference on Recent Trends in Computer Science and Technology (ICRTCST), IEEE, Apr. 2024, pp. 227–232. doi: 10.1109/ICRTCST61793.2024.10578372.
[12] A. R. H. Dwika and D. Avianto, “Implementasi Algoritma LSTM untuk Prediksi Harga Cabai Merah Keriting di Yogyakarta,” J. Indones. Manaj. Inform. dan Komun., vol. 5, no. 1, pp. 635–648, 2024, doi: 10.35870/jimik.v5i1.534.
[13] I. Malashin, V. Tynchenko, A. Gantimurov, V. Nelyub, and A. Borodulin, “Applications of Long Short-Term Memory (LSTM) Networks in Polymeric Sciences: A Review,” Polymers (Basel)., vol. 16, no. 18, pp. 1–44, 2024, doi: 10.3390/polym16182607.
[14] T. Yang, Y. Cheng, Y. Ren, Y. Lou, M. Wei, and H. Xin, “A Deep Learning Framework for Sequence Mining with Bidirectional LSTM and Multi-Scale Attention,” Proc. 2025 2nd Int. Conf. Innov. Manag. Inf. Syst. ICIIS 2025, pp. 472–476, 2025, doi: 10.1145/3745676.3745751.
[15] D. R. I. M. Setiadi, A. R. Muslikh, S. W. Iriananda, W. Warto, J. Gondohanindijo, and A. A. Ojugo, “Outlier Detection Using Gaussian Mixture Model Clustering to Optimize XGBoost for Credit Approval Prediction,” J. Comput. Theor. Appl., vol. 2, no. 2, pp. 244–255, 2024, doi: 10.62411/jcta.11638.
[16] E. Tjoa and C. Guan, “A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI,” IEEE Trans. Neural Networks Learn. Syst., vol. 32, no. 11, pp. 4793–4813, 2021, doi: 10.1109/TNNLS.2020.3027314.
[17] M. Sarkar, “Explainable AI In E-Commerce: Enhancing Trust And Transparency In AI-Driven Decisions,” Innov. Eng. J., vol. 2, no. 01, pp. 12–39, Jan. 2024, doi: 10.70937/itej.v2i01.53.
[18] A. Prashanthan, R. Roshan, and M. Maduranga, “RetenNet: A Deployable Machine Learning Pipeline with Explainable AI and Prescriptive Optimization for Customer Churn Management,” J. Futur. Artif. Intell. Technol., vol. 2, no. 2, pp. 182–201, 2025, doi: 10.62411/faith.3048-3719-110.
[19] B. P. Chamberlain, Â. Cardoso, C. H. Bryan Liu, R. Pagliari, and M. P. Deisenroth, “Customer lifetime value prediction using embeddings,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. Part F1296, pp. 1753–1762, 2017, doi: 10.1145/3097983.3098123.
[20] M. G. S. P. Kusuma et al., “Integrating Quantum, Deep, and Classic Features with Attention-Guided AdaBoost for Medical Risk Prediction,” J. Comput. Theor. Appl., vol. 3, no. 2, pp. 171–189, Oct. 2025, doi: 10.62411/jcta.14873.
[21] A. M. Salih et al., “A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME,” Adv. Intell. Syst., 2024, doi: 10.1002/aisy.202400304.
[22] T. R. Noviandy, G. M. Idroes, and I. Hardi, “An Interpretable Machine Learning Strategy for Antimalarial Drug Discovery with LightGBM and SHAP,” J. Futur. Artif. Intell. Technol., vol. 1, no. 2, pp. 84–95, 2024, doi: 10.62411/faith.2024-16.
[23] B. I. Igoche, O. Matthew, P. Bednar, and A. Gegov, “Integrating Structural Causal Model Ontologies with LIME for Fair Machine Learning Explanations in Educational Admissions,” J. Comput. Theor. Appl., vol. 2, no. 1, pp. 65–85, 2024, doi: 10.62411/jcta.10501.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Yulian Dwi Nartriani, De Rosal Ignatius Moses Setiadi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
