3066-280XISSN (Online)
Volume 3 , Issue 1 , PP: 36-48, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Mostafa Abotaleb 1 *
Doi: https://doi.org/10.54216/MOR.030104
This review aims to demonstrate the effectiveness of the ML and DL approaches to demand forecasting in the retail supply chain, proving the superiority of the approaches over conventional statistical methods. Traditional models suit themselves poorly in the face of nonlinear dependencies, outside influences and fluctuating settings, especially in retail. At the same time, Machine Learning methodologies like RandomForest, SVMs, LSTM, and CNN provide astonishing accuracy once the temporal and spatial complexity characteristics of sales information are discovered. The review underlines the consideration of data fusion and feature construction, including macroeconomic indexes, weather, and promotions, in extending the forecasts. Issues like data quality, scalability and interpretability of the model are deliberated upon along with the solutions related to incorporating IoT and blockchain. These innovations imply real-time data capture, high-reliability levels and greater process transparency. On the same note, using enhanced value assessment indicators, usually MAE, RMSE, and MAPE, highlights that model engineering requires careful, distinct selection methods. Thus, this systematic review has put together and analyzed the most recent developments, issues, and trends in applying ML and DL in enhancing inventory management, pricing, and customer satisfaction in the retail industry to stimulate better performance and competitiveness in today's fast-growing market environment.
Machine Learning , Deep Learning , Retail Demand Forecasting , Data Integration , Feature Engineering , Supply Chain Management.
[1] M. S. Haque, M. S. Amin, and J. Miah, “Retail Demand Forecasting: A Comparative Study for Multivariate Time Series,” Aug. 2023, Accessed: Dec. 24, 2024. [Online]. Available: https://arxiv.org/abs/2308.11939v1
[2] M. A. Jahin, A. Shahriar, and M. Al Amin, “MCDFN: Supply Chain Demand Forecasting via an Explainable Multi-Channel Data Fusion Network Model,” May 2024, Accessed: Dec. 24, 2024. [Online]. Available: https://arxiv.org/abs/2405.15598v4
[3] X. Bi, G. Adomavicius, W. Li, and A. Qu, “Improving Sales Forecasting Accuracy: A Tensor Factorization Approach with Demand Awareness,” INFORMS J Comput, vol. 34, no. 3, pp. 1644–1660, Nov. 2020, doi: 10.1287/ijoc.2021.1147.
[4] “Supervised Machine Learning - GeeksforGeeks.” Accessed: Dec. 24, 2024. [Online]. Available: https://www.geeksforgeeks.org/supervised-machine-learning/?utm_source=chatgpt.com
[5] P. Laurinec and M. Lucká, "Usefulness of Unsupervised Ensemble Learning Methods for Time Series Forecasting of Aggregated or Clustered Load," doi: 10.1007/978-3-319-78680-3_9.
[6] S. S. J. Nithin, T. Rajasekar, S. Jayanthy, K. Karthik, and R. R. Rithick, “Retail Demand Forecasting using CNN-LSTM Model,” Proceedings of the International Conference on Electronics and Renewable Systems, ICEARS 2022, pp. 1751–1756, 2022, doi: 10.1109/ICEARS53579.2022.9752283.
[7] S. S. J. Nithin, T. Rajasekar, S. Jayanthy, K. Karthik, and R. R. Rithick, “Retail Demand Forecasting using CNN-LSTM Model,” Proceedings of the International Conference on Electronics and Renewable Systems, ICEARS 2022, pp. 1751–1756, 2022, doi: 10.1109/ICEARS53579.2022.9752283.
[8] N. Shaik, A. Subhahan Shaik, and D. Krishna Priya, “Elevating Machine Learning Performance: The Power of Feature Engineering,” 2024.
[9] “MSE vs RMSE vs MAE vs MAPE vs R-Squared: When to Use?” Accessed: Dec. 24, 2024. [Online]. Available: https://vitalflux.com/mse-vs-rmse-vs-mae-vs-mape-vs-r-squared-when-to-use/?utm_source=chatgpt.com
[10] R. J. Kotak and R. Rakholia, “A Comprehensive Study on Different Machine Learning Approaches for Retail Sales Forecasting: Methods, Procedures, Obstacles, and Prospects,” Lecture Notes in Networks and Systems, vol. 1095 LNNS, pp. 529–541, 2024, doi: 10.1007/978-981-97-6318-4_41/FIGURES/3.
[11] P. Raoufi, A. Hemmati, and A. M. Rahmani, “Deep learning applications in the Internet of Things: a review, tools, and future directions,” Evol Intell, vol. 17, no. 5, pp. 3621–3654, Oct. 2024, doi: 10.1007/S12065-024-00949-0/METRICS.
[12] S. D’Souza, D. Shah, A. Allati, and P. Soni, “Making forecasting self-learning and adaptive -- Pilot forecasting rack,” Jun. 2023, Accessed: Dec. 25, 2024. [Online]. Available: https://arxiv.org/abs/2306.07305v1
[13] N. Ampazis, “Forecasting Demand in Supply Chain Using Machine Learning Algorithms,” https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJALR.2015010104, vol. 5, no. 1, pp. 56–73, Jan. 1AD, doi: 10.4018/IJALR.2015010104.
[14] M. A. Jahin, A. Shahriar, and M. Al Amin, “MCDFN: Supply Chain Demand Forecasting via an Explainable Multi-Channel Data Fusion Network Model,” May 2024, Accessed: Dec. 25, 2024. [Online]. Available: https://arxiv.org/abs/2405.15598v4
[15] X. Bi, G. Adomavicius, W. Li, and A. Qu, “Improving Sales Forecasting Accuracy: A Tensor Factorization Approach with Demand Awareness,” INFORMS J Comput, vol. 34, no. 3, pp. 1644–1660, Nov. 2020, doi: 10.1287/ijoc.2021.1147.
[16] M. S. Haque, M. S. Amin, and J. Miah, “Retail Demand Forecasting: A Comparative Study for Multivariate Time Series,” Aug. 2023, Accessed: Dec. 25, 2024. [Online]. Available: https://arxiv.org/abs/2308.11939v1
[17] A. ul Husna, S. H. Amin, and A. Ghasempoor, “Demand Forecasting Using Machine Learning and Deep Learning Approaches in the Retail Industry: A Comparative Study,” pp. 260–265, 2023, doi: 10.1007/978-3-031-25847-3_24.
[18] G. Di Gravio et al., “Applying Machine Learning in Retail Demand Prediction—A Comparison of Tree-Based Ensembles and Long Short-Term Memory-Based Deep Learning,” Applied Sciences 2023, Vol. 13, Page 11112, vol. 13, no. 19, p. 11112, Oct. 2023, doi: 10.3390/APP131911112.
[19] A. Mitra, A. Jain, A. Kishore, and P. Kumar, “A Comparative Study of Demand Forecasting Models for a Multi-Channel Retail Company: A Novel Hybrid Machine Learning Approach,” Operations Research Forum, vol. 3, no. 4, pp. 1–22, Dec. 2022, doi: 10.1007/S43069-022-00166-4/FIGURES/2.
[20] S. Mukherjee et al., “ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting,” Mar. 2018, Accessed: Dec. 25, 2024. [Online]. Available: https://arxiv.org/abs/1803.03800v2
[21] X. Bi, G. Adomavicius, W. Li, and A. Qu, “Improving Sales Forecasting Accuracy: A Tensor Factorization Approach with Demand Awareness,” INFORMS J Comput, vol. 34, no. 3, pp. 1644–1660, Nov. 2020, doi: 10.1287/ijoc.2021.1147.
[22] M. S. Haque, M. S. Amin, and J. Miah, “Retail Demand Forecasting: A Comparative Study for Multivariate Time Series,” Aug. 2023, Accessed: Dec. 25, 2024. [Online]. Available: https://arxiv.org/abs/2308.11939v1
[23] E. ; Aldahmani et al., “Demand Forecasting in Supply Chain Using Uni-Regression Deep Approximate Forecasting Model,” Applied Sciences 2024, Vol. 14, Page 8110, vol. 14, no. 18, p. 8110, Sep. 2024, doi: 10.3390/APP14188110.
[24] A. Mitra, A. Jain, A. Kishore, and P. Kumar, “A Comparative Study for Machine Learning Models in Retail Demand Forecasting,” Smart Innovation, Systems and Technologies, vol. 316, pp. 273–282, 2023, doi: 10.1007/978-981-19-5403-0_23/TABLES/2.
[25] N. Ampazis, “Forecasting Demand in Supply Chain Using Machine Learning Algorithms,” https://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJALR.2015010104, vol. 5, no. 1, pp. 56–73, Jan. 1AD, doi: 10.4018/IJALR.2015010104.
[26] K. Douaioui, R. Oucheikh, O. Benmoussa, and C. Mabrouki, “Machine Learning and Deep Learning Models for Demand Forecasting in Supply Chain Management: A Critical Review,” Applied System Innovation 2024, Vol. 7, Page 93, vol. 7, no. 5, p. 93, Sep. 2024, doi: 10.3390/ASI7050093.
[27] T. Shakir and A. Modupe, “Enhancing Demand Forecasting in Retail Supply Chains: A Machine Learning Regression Approach,” Global Journal of Management and Business Research, vol. 23, no. A8, pp. 1–15, Oct. 2023, Accessed: Dec. 25, 2024. [Online]. Available: https://journalofbusiness.org/index.php/GJMBR/article/view/102919
[28] S. Mukherjee et al., “ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting,” Mar. 2018, Accessed: Dec. 27, 2024. [Online]. Available: https://arxiv.org/abs/1803.03800v1
[29] M. J. Samonte et al., "Applying Deep Learning for the Prediction of Retail Store Sales."
[30] G. Di Gravio et al., “Applying Machine Learning in Retail Demand Prediction—A Comparison of Tree-Based Ensembles and Long Short-Term Memory-Based Deep Learning,” Applied Sciences 2023, Vol. 13, Page 11112, vol. 13, no. 19, p. 11112, Oct. 2023, doi: 10.3390/APP131911112.
[31] P. Ganguly and I. Mukherjee, “Enhancing Retail Sales Forecasting with Optimized Machine Learning Models,” 2024 4th International Conference on Sustainable Expert Systems (ICSES), pp. 884–889, Oct. 2024, doi: 10.1109/ICSES63445.2024.10762950.
[32] S. Mejía and J. Aguilar, “A demand forecasting system of product categories defined by their time series using a hybrid approach of ensemble learning with feature engineering,” Computing, vol. 106, no. 12, pp. 3945–3965, Dec. 2024, doi: 10.1007/S00607-024-01320-Y/TABLES/12.
[33] D. Salinas, V. Flunkert, J. Gasthaus, and T. Januschowski, “DeepAR: Probabilistic forecasting with autoregressive recurrent networks,” Int J Forecast, vol. 36, no. 3, pp. 1181–1191, Jul. 2020, doi: 10.1016/j.ijforecast.2019.07.001.
