An Evolving Memory Ensemble For Accurate Dual-Target Retail Transaction Forecasting
DOI:
https://doi.org/10.29284/s4mkmh87Keywords:
Retail Analytics, Evolving Memory Ensemble, Adaptive Learning, Concept Drift, Time-Series Prediction, Dual-Target Regression.Abstract
Incorrect forecasting of the outcomes of retail transactions is critical to successful inventory management, pricing, and customer-oriented decision-making. Retail data streams however are dynamic in nature with time variations, seasonality and customer behavioral changes that present a challenge to the conventional old-fashioned prediction models. The paper will overcome these issues by suggesting a new Evolving Memory Ensemble (EME) structure of dual-target retail prediction, which is based on Total Cost and Total Items purchased per transaction. The offered solution combines the window-based learning, segmentation via clustering and memory-aware evolution of ensembles to constantly adapt to evolving data distributions. The framework is tested in a rigorous time-based and walk-forward experimental framework using a real-world retail dataset of 30,000 transactions gathered in 2020-2023. Empirical findings indicate that EME framework shows stable and reliable predictive performance because of dynamically updating the model relevance using exponential moving average tracking of errors. These results indicate the usefulness of adaptive learning based on memory in managing concept drift and emphasize the practical utility of the suggested solution in the case of retail analytics systems in the real world.
References
[1] Khan, M. A., Saqib, S., Alyas, T., Ur Rehman, A., Saeed, Y., Zeb, A., Zareei, M., & Mohamed, E. M. (2020). Effective Demand Forecasting Model Using Business Intelligence Empowered with Machine Learning. IEEE Access, 8, 116013–116023. https://doi.org/10.1109/ACCESS.2020.3003790
[2] Kohli, S., Godwin, G. T., & Urolagin, S. (2020). Sales prediction using linear and KNN regression. In Advances in Machine Learning and Computational Intelligence: Proceedings of ICMLCI 2019 (pp. 321-329). Singapore: Springer Singapore.
[3] Feizabadi, J. (2022). Machine learning demand forecasting and supply chain performance. International Journal of Logistics Research and Applications, 25(2), 119–142. https://doi.org/10.1080/13675567.2020.1803246
[4] Usman, S., Hayat, A., Ashraf, M. U., Sajawal, M., & Alshaikh, H. S. (2023). Predictive Analysis of Retail Sales Forecasting using Machine Learning Techniques. https://doi.org/10.54692/lgurjcsit.2022.06004399
[5] Weng, T., Liu, W., & Xiao, J. (2020). Supply chain sales forecasting based on lightGBM and LSTM combination model. Industrial Management and Data Systems, 120(2), 265–279. https://doi.org/10.1108/IMDS-03-2019-0170
[6] Rahman Mahin, M. P., Shahriar, M., Das, R. R., Roy, A., & Reza, A. W. (2025). Enhancing Sustainable Supply Chain Forecasting Using Machine Learning for Sales Prediction. Procedia Computer Science, 252, 470–479. https://doi.org/10.1016/j.procs.2025.01.006
[7] Alatawi, M. N. (2025). Detection of fraud in IoT based credit card collected dataset using machine learning. Machine Learning with Applications, 19, 100603. https://doi.org/10.1016/j.mlwa.2024.100603
[8] Karakaya, İ. (2025). Evaluation of Machine Learning and Ensemble Learning Models for Classification Using Delivery Data. Verimlilik Dergisi, PRODUCTIVITY FOR LOGISTICS, 89–104. https://doi.org/10.51551/verimlilik.1526436
[9] Rafi, M. D. A. L., Rodrigues, G. N., Mir, M. N. H., Bhuiyan, M. S. M., Mridha, M. F., Islam, M. R., & Watanobe, Y. (2025). A hybrid Temporal Convolutional Network and Transformer Model for Accurate and Scalable Sales Forecasting. IEEE Open Journal of the Computer Society.
https://doi.org/10.1109/OJCS.2025.3538579
[10] Tkachuk, S., Łukasik, S., & Wróblewska, A. (2024). Consumer Transactions Simulation through Generative Adversarial Networks. https://doi.org/10.3390/electronics14020284
[11] Bhatia, K., Professor, A., & Gupta, B. (2025). International Journal of Web of Multidisciplinary Studies Predictive Analytics for Customer Behavior and Sales Forecasting in Retail. 2(1), 24–30. http://creativecommons.org/licenses/by/4.0/
[12] Kizgin, K. T., Alp, S., Aydin, N., & Yu, H. (2025). Machine learning-based sales forecasting during crises: Evidence from a Turkish women’s clothing retailer. Science Progress, 108(1). https://doi.org/10.1177/00368504241307719
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
