COMPARATIVE ANALYSIS OF LSTM, ARIMA, AND LINEAR REGRESSION FOR E-COMMERCE SALES PRICE PREDICTION
DOI:
https://doi.org/10.63503/c.acset.2025.4Keywords:
E-Commerce, Sales Price Prediction, Machine Learning, Time Series Forecasting, LSTM (Long Short-Term Memory), ARIMAAbstract
In the rapidly evolving landscape of e-commerce, accurate price prediction and sales forecasting have become vital for operational efficiency, inventory management, and strategic decision-making. This study presents a comprehensive methodology employing preprocessing techniques, normalization strategies, data splitting, and advanced modeling—specifically Linear Regression, Long Short-Term Memory (LSTM), and AutoRegressive Integrated Moving Average (ARIMA) to predict product sales prices using an E-Commerce Sales dataset. The raw data undergoes missing-value handling and column pruning to enhance relevancy. Subsequently, normalization is applied through both MinMax and Standard Scaler techniques to ensure scale uniformity. The preprocessed dataset is then partitioned into training and test sets, facilitating both model evaluation and predictive capability assessment. Performance is quantified using key metrics—Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) accompanied by comparative visualizations. Our findings demonstrate the strengths and trade-offs of each algorithm in forecasting accuracy, showcasing their potential for real-world e‑commerce applications. By illustrating the comparative performance of traditional statistical techniques and deep learning models, the study provides a roadmap for stakeholders to choose appropriate forecasting tools aligned with their business needs.
References
1. Banerjee, P., Prasad, V., Thakur, K., Mitra, D., Gaurav, K., & Kanrar, S. Predictive modeling and dynamic analysis of price trends in e-commerce using ML technique. In IEEE International Conference on Networks, Knowledge, and Convergence (NKCon). 2024. 21–22 September 2024. DOI:10.1109/NKCon62728.2024.10774870
2. Hu, Y., Zhou, Z., & Wang, T. Stock price prediction of e-commerce platforms under COVID-19’s influence based on machine learning. In IEEE International Conference on Machine Learning for Intelligent Systems Engineering (MLISE). 2022. 05–07 August 2022. DOI:10.1109/MLISE57402.2022.00092
3. Telkar, K., Kandarkar, G., Tola, A., Bagade, J., & Bhimanpallewar, R. Prediction of laptop prices with recommendations based on user specifications. In IEEE International Conference on Computing, Communication, Control and Automation (ICCUBEA). 2023. DOI:10.1109/ICCUBEA58933.2023.10392000
4. Goyal, H., Sukhija, A., Bhatia, K., Guleria, K., & Sharma, S. Demand prediction of consumer intention to buy edible items using machine learning techniques. In IEEE International Conference on Smart Generation Computing, Communication and Networking (SMARTGENCON). 2023. 29–31 December 2023. DOI:10.1109/SMARTGENCON60755.2023.10442766
5. Alrumiah, S.S., & Hadwan, M. Implementing big data analytics in e-commerce: Vendor and customer view. IEEE Access, 2021. 9: p.3063615. DOI:10.1109/ACCESS.2021.3063615
6. Almuqren, L., Alruwais, N., Alhashmi, A.A., Alzahrani, I.R., Salih, N., & Assiri, M. WSN-assisted consumer purchasing power prediction via Barracuda Swarm Optimization-driven deep learning for e-commerce systems. IEEE Transactions on Consumer Electronics, 2024. 70(2): p.1694–1701. DOI:10.1109/TCE.2024.3371249
7. Zhang, C., Wang, X., Zhao, C., Ren, Y., Zhang, T., & Peng, Z. PromotionLens: Inspecting promotion strategies of online e-commerce via visual analytics. IEEE Transactions on Visualization and Computer Graphics, 2022. 29(2): p.767–777. DOI:10.1109/TVCG.2022.3209440
8. Dritsas, E., & Trigka, M. Machine learning in e-commerce: Trends, applications, and future challenges. IEEE Access, 2025. 13: p.99048–99067. DOI:10.1109/ACCESS.2025.3572865
9. Trần Quang, P.L., Ngo, U., & Vo Nhi, A.D. E-commerce price suggestion algorithm: A machine learning application. Innovation in Industry Journal, 2022. DOI:10.46254/IN02.20220609
10. Akram, A., & Arun, M. E-commerce product sales prediction using machine learning. International Journal of Innovative Research in Computer Science & Technology, 2025. 6(2): p.2149–2151.
11. Chen, Y., Xie, X., Pei, Z., Yi, W., Wang, C., Zhang, W., & Ji, Z. Development of a time series e-commerce sales prediction method for short-shelf-life products using GRU-LightGBM. Applied Sciences, 2024. 14(2):866. https://doi.org/10.3390/app14020866
12. Wang, C., & Wang, J. Research on e-commerce inventory sales forecasting model based on ARIMA and LSTM algorithm. Mathematics, 2025. 13(11):1838. https://doi.org/10.3390/math13111838
13. Nowak, M., & Pawłowska-Nowak, M. Dynamic pricing method in the e-commerce industry using machine learning. Applied Sciences, 2024. 14(24):11668. https://doi.org/10.3390/app142411668
14. Gkikas, D.C., & Theodoridis, P.K. Predicting online shopping behavior: Using machine learning and Google Analytics to classify user engagement. Applied Sciences, 2024. 14(23):11403. https://doi.org/10.3390/app142311403
