Exploring Explainability in Multi-Category Electronic Markets: A Comparison of Machine Learning and Deep Learning Approaches
DOI:
https://doi.org/10.62411/faith.3048-3719-58Keywords:
Artificial Intelligence, Deep Learning, Electronic Markets, Explainable Artificial Intelligence, Information Systems, Machine Learning, PredictionAbstract
Artificial intelligence can change many industries as a global phenomenon. Over the years, this transformation has supported Electronic Markets in reengineering the processes and activities that take place in traditional markets, focusing on improving transaction effectiveness and efficiency. While our dependence on intelligent machines continues to grow, the demand for more transparent and interpretable models equally grows. Thus, explanations for machine decisions and predictions are needed to justify their reliability, which requires greater interpretability and often elaborates the need to understand the algorithms' underlying mechanism. This paper, therefore, proposed models based on Decision Tree (DT), Long Short-Term Memory (LSTM), and an ensemble of the two aforementioned models for improving CLV accuracy, interpretability, and explainability of AI-based models in the multi-category electronic market. An open-source e-commerce Behavior Data from a multi-category store, previously used by similar studies on XAI and CLV, was used in this experiment, ensuring the robustness of the product prediction and explanations and fair comparison. From the results, the models from this study demonstrated remarkable performance in terms of minimal error rates of MAE, MSE, and RMSE, with LSTM outperforming the other models. Regarding explainability and interpretation, the begin_time is ranked as the most relevant feature in CLV prediction.
Downloads
References
R. Dwivedi et al., “Explainable AI (XAI): Core Ideas, Techniques, and Solutions,” ACM Comput. Surv., vol. 55, no. 9, pp. 1–33, Sep. 2023, doi: 10.1145/3561048.
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, Nov. 2021, doi: 10.1109/TNNLS.2020.3027314.
F. Sovrano, S. Sapienza, M. Palmirani, and F. Vitali, “Metrics, Explainability and the European AI Act Proposal,” J, vol. 5, no. 1, pp. 126–138, Feb. 2022, doi: 10.3390/j5010010.
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, pp. 1–37, Oct. 2021, doi: 10.1145/3441444.
H. Aeron, A. Kumar, and J. Moorthy, “Data mining framework for customer lifetime value-based segmentation,” J. Database Mark. Cust. Strateg. Manag., vol. 19, no. 1, pp. 17–30, Mar. 2012, doi: 10.1057/dbm.2012.1.
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,” Information, vol. 13, no. 8, p. 373, Aug. 2022, doi: 10.3390/info13080373.
L. Ryals and S. Knox, “Measuring and managing customer relationship risk in business markets,” Ind. Mark. Manag., vol. 36, no. 6, pp. 823–833, Aug. 2007, doi: 10.1016/j.indmarman.2006.06.017.
T. T. Win and K. S. Bo, “Predicting Customer Class using Customer Lifetime Value with Random Forest Algorithm,” in 2020 International Conference on Advanced Information Technologies (ICAIT), Nov. 2020, pp. 236–241. doi: 10.1109/ICAIT51105.2020.9261792.
Y. Sun, H. Liu, and Y. Gao, “Research on customer lifetime value based on machine learning algorithms and customer relationship management analysis model,” Heliyon, vol. 9, no. 2, p. e13384, Feb. 2023, doi: 10.1016/j.heliyon.2023.e13384.
S.-Y. Kim, T.-S. Jung, E.-H. Suh, and H.-S. Hwang, “Customer segmentation and strategy development based on customer lifetime value: A case study,” Expert Syst. Appl., vol. 31, no. 1, pp. 101–107, Jul. 2006, doi: 10.1016/j.eswa.2005.09.004.
I. Ahmed, G. Jeon, and F. Piccialli, “From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and Where,” IEEE Trans. Ind. Informatics, vol. 18, no. 8, pp. 5031–5042, Aug. 2022, doi: 10.1109/TII.2022.3146552.
N. Radulovic, “Post-hoc Explainable AI for Black Box Models on Tabular Data,” Institut Polytechnique de Paris, 2023. Accessed: Mar. 17, 2024. [Online]. Available: https://theses.hal.science/tel-04362470/file/107534_RADULOVIC_2023_archivage.pdf
P. Jiang, H. Suzuki, and T. Obi, “XAI-based cross-ensemble feature ranking methodology for machine learning models,” Int. J. Inf. Technol., vol. 15, no. 4, pp. 1759–1768, Apr. 2023, doi: 10.1007/s41870-023-01270-2.
K. Bauer, O. Hinz, W. van der Aalst, and C. Weinhardt, “Expl(AI)n It to Me – Explainable AI and Information Systems Research,” Bus. Inf. Syst. Eng., vol. 63, no. 2, pp. 79–82, Apr. 2021, doi: 10.1007/s12599-021-00683-2.
D. Monner and J. A. Reggia, “A generalized LSTM-like training algorithm for second-order recurrent neural networks,” Neural Networks, vol. 25, pp. 70–83, Jan. 2012, doi: 10.1016/j.neunet.2011.07.003.
O. Günlük, J. Kalagnanam, M. Li, M. Menickelly, and K. Scheinberg, “Optimal decision trees for categorical data via integer programming,” J. Glob. Optim., vol. 81, no. 1, pp. 233–260, Sep. 2021, doi: 10.1007/s10898-021-01009-y.
H. G. Lee and T. H. Clark, “Market Process Reengineering through Electronic Market Systems: Opportunities and Challenges,” J. Manag. Inf. Syst., vol. 13, no. 3, pp. 113–136, Dec. 1996, doi: 10.1080/07421222.1996.11518136.
Y. Xing, L. Yu, J. Z. Zhang, and L. J. Zheng, “Uncovering the Dark Side of Artificial Intelligence in Electronic Markets,” J. Organ. End User Comput., vol. 35, no. 1, pp. 1–25, Aug. 2023, doi: 10.4018/JOEUC.327278.
L. T. Khrais, “Role of Artificial Intelligence in Shaping Consumer Demand in E-Commerce,” Futur. Internet, vol. 12, no. 12, p. 226, Dec. 2020, doi: 10.3390/fi12120226.
S. Shin, J.-U. Won, and M. Kim, “Comparative research on DNN and LSTM algorithms for soot emission prediction under transient conditions in a diesel engine,” J. Mech. Sci. Technol., vol. 37, no. 6, pp. 3141–3150, Jun. 2023, doi: 10.1007/s12206-023-0538-y.
H.-R. Lou, X. Wang, Y. Gao, and Q. Zeng, “Comparison of ARIMA model, DNN model and LSTM model in predicting disease burden of occupational pneumoconiosis in Tianjin, China,” BMC Public Health, vol. 22, no. 1, p. 2167, Nov. 2022, doi: 10.1186/s12889-022-14642-3.
J. Brasse, H. R. Broder, M. Förster, M. Klier, and I. Sigler, “Explainable artificial intelligence in information systems: A review of the status quo and future research directions,” Electron. Mark., vol. 33, no. 1, p. 26, Dec. 2023, doi: 10.1007/s12525-023-00644-5.
B. Lantz, Machine learning with r: Expert techniques for predictive modeling. Packt, 2019. [Online]. Available: https://books.google.com.ng/books?id=IiWewwEACAAJ
M. Ranjith Kumar, P. S, J. Srinivasan Anusha, V. Chatiyode, J. Santiago, and D. Chaudhary, “Enhancing Telecommunications Customer Retention: A Deep Learning Approach Using LSTM for Predictive Churn Analysis,” in 2024 International Conference on Data Science and Network Security (ICDSNS), Jul. 2024, pp. 01–07. doi: 10.1109/ICDSNS62112.2024.10691038.
N. Sahoo, P. V Singh, and T. Mukhopadhyay, “A Hidden Markov Model for Collaborative Filtering,” MIS Q., vol. 36, no. 4, pp. 1329–1356, 2012, [Online]. Available: https://dl.acm.org/doi/abs/10.5555/2481674.2481689
S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017.
C. Molnar, Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. LeanPub, 2020. [Online]. Available: https://christophm.github.io/interpretable-ml-book/
D. Gunning, E. Vorm, J. Y. Wang, and M. Turek, “DARPA’s explainable AI (XAI) program: A retrospective,” Appl. AI Lett., vol. 2, no. 4, Dec. 2021, doi: 10.1002/ail2.61.
M. Van Lent, W. Fisher, and M. Mancuso, “An Explainable Artificial Intelligence System for Small-unit Tactical Behavior,” in IAAI’04: Proceedings of the 16th conference on Innovative applications of artifical intelligence, 2004, pp. 900–907. Accessed: Mar. 16, 2024. [Online]. Available: https://dl.acm.org/doi/10.5555/1597321.1597342
A. Barredo Arrieta et al., “Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI,” Inf. Fusion, vol. 58, pp. 82–115, Jun. 2020, doi: 10.1016/j.inffus.2019.12.012.
S. Maksymiuk, A. Gosiewska, and P. Biecek, “Landscape of R packages for eXplainable Artificial Intelligence,” arXiv. Cornell University, Sep. 24, 2020. doi: 10.48550/arxiv.2009.13248.
A. M. Salih et al., “A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME,” Adv. Intell. Syst., vol. 7, no. 1, Jan. 2025, doi: 10.1002/aisy.202400304.
M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why Should I Trust You?,’” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2016, pp. 1135–1144. doi: 10.1145/2939672.2939778.
S. Zhao et al., “perCLTV: A General System for Personalized Customer Lifetime Value Prediction in Online Games,” ACM Trans. Inf. Syst., vol. 41, no. 1, pp. 1–29, Jan. 2023, doi: 10.1145/3530012.
B. P. Chamberlain, Â. Cardoso, C. H. B. Liu, R. Pagliari, and M. P. Deisenroth, “Customer Lifetime Value Prediction Using Embeddings,” in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2017, pp. 1753–1762. doi: 10.1145/3097983.3098123.
X. Wang, T. Liu, and J. Miao, “A Deep Probabilistic Model for Customer Lifetime Value Prediction,” arXiv. ARXIV, 2019. [Online]. Available: https://arxiv.org/pdf/1912.07753
H.-H. Chang and T.-S. Yang, “Consumer rights or unethical behaviors: Exploring the impacts of retailer return policies,” J. Retail. Consum. Serv., vol. 64, p. 102779, Jan. 2022, doi: 10.1016/j.jretconser.2021.102779.
A. Madhuri, “‘Exploring the Role of Personalization in E-commerce: Impacts on Consumer Trust and Purchase Intentions,’” Eur. Econ. Lett., vol. 14, no. 3, pp. 907–919, 2024, doi: 10.52783/eel.v14i3.1845.
D. P. Sakas, D. P. Reklitis, N. T. Giannakopoulos, and P. Trivellas, “The influence of websites user engagement on the development of digital competitive advantage and digital brand name in logistics startups,” Eur. Res. Manag. Bus. Econ., vol. 29, no. 2, p. 100221, May 2023, doi: 10.1016/j.iedeen.2023.100221.
X. Wang, Y. Wang, D. Liu, Y. Wang, and Z. Wang, “Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM,” Sci. Rep., vol. 13, no. 1, p. 14876, Sep. 2023, doi: 10.1038/s41598-023-41537-z.
V. Kumar and W. Reinartz, “Creating Enduring Customer Value,” J. Mark., vol. 80, no. 6, pp. 36–68, Nov. 2016, doi: 10.1509/jm.15.0414.
R. E. Ako et al., “Effects of Data Resampling on Predicting Customer Churn via a Comparative Tree-based Random Forest and XGBoost,” J. Comput. Theor. Appl., vol. 2, no. 1, pp. 86–101, Jun. 2024, doi: 10.62411/jcta.10562.
C. E. Durango Vanegas, J. C. Giraldo Mejía, F. A. Vargas Agudelo, and D. E. Soto Duran, “A Representation Based on Essence for the CRISP-DM Methodology,” Comput. y Sist., vol. 27, no. 3, Sep. 2023, doi: 10.13053/cys-27-3-3446.
T. G. Dietterich, “Ensemble methods in machine learning,” in MCS ’00: Proceedings of the First International Workshop on Multiple Classifier Systems, 2000, pp. 1–15. [Online]. Available: https://dl.acm.org/doi/10.5555/648054.743935
O. Sagi and L. Rokach, “Ensemble learning: A survey,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 8, no. 4, pp. 1–18, 2018, doi: 10.1002/widm.1249.
D. Opitz and R. Maclin, “Popular Ensemble Methods: An Empirical Study,” J. Artif. Intell. Res., vol. 11, pp. 169–198, Aug. 1999, doi: 10.1613/jair.614.
C. Zhang, S. Bengio, M. Hardt, B. Recht, and O. Vinyals, “Understanding deep learning (still) requires rethinking generalization,” Commun. ACM, vol. 64, no. 3, pp. 107–115, Mar. 2021, doi: 10.1145/3446776.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Suleiman Adamu, Aamo Iorliam, Özcan Asilkan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
