The Future of Retail Forecasting: A Comparative Study for Enhanced Store Performance

Mian Usman Sattar; Abdul Ghaffar

doi:10.69565/jems.v4i1.414

Authors

Mian Usman Sattar Lecture School of Science and engineering, Department of Computing. University of Derby, United Kingdom https://orcid.org/0000-0003-1457-3021
Abdul Ghaffar Assistant Professor Dr Hasan Murad School of Management UMT https://orcid.org/0000-0003-0792-9261

DOI:

https://doi.org/10.69565/jems.v4i1.414

Keywords:

Machine Learning, Deep Learning, Inventory Management, Marketing Strategies, Forecasting

Abstract

Accurate forecasts of sales are vital for retailers to efficiently plan inventory, refine marketing strategies, and achieve regional sales targets. The traditional forecasting methods are deficient in capturing complex patterns and seasonal changes, especially in an increasingly data-driven market. This research employs advanced machine learning models, namely ARIMA (AutoRegressive Integrated Moving Average), LSTM (Long Short-Term Memory), and its Hybrid PSO-LSTM (Particle Swarm Optimization-LSTM) model, to forecast retail sales in the period 2014-2021. The study finds that although ARIMA is easy to use and quick to model and implement, LSTM and PSO-LSTM models (especially the latter) are more accurate and robust. PSO-LSTM is more time-consuming, but it is the more accurate and structural forecasting model, with detailed analyses that could help develop long-term plans for the company. In terms of accuracy, the PSO-LSTM model outperformed others, achieving a Mean Absolute Error (MAE) of 15,282 and a Root Mean Square Error (RMSE) of 21,459. The LSTM model followed closely with an MAE of 15,441 and RMSE of 21,792. ARIMA1 and ARIMA2 models had slightly higher errors, with ARIMA1 reporting an MAE of 15,460 and RMSE of 21,557, and ARIMA2 reporting an MAE of 15,547 and RMSE of 21,652. These results confirm the superiority of machine learning models, with PSO-LSTM providing the best overall performance. These findings present the potential of advanced analytics for retail for improved operational efficiency. This research conducts a comprehensive analysis of forecasting models and provides useful guidelines for applying these models in a highly competitive business environment.

References

Angeletos, G. M., Lian, C., & Wolf, C. K. (2024). Can deficits finance themselves? Econometrica, 92(5), 1351–1390. https://doi.org/10.3982/ECTA21791

Apache Spark. (2025, May 19). PySpark overview. https://spark.apache.org/docs/latest/api/python/index.html

Bandara, K., Bergmeir, C., & Smyl, S. (2020). Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach. Expert Systems with Applications, 140, Article e112896. https://doi.org/10.1016/j.eswa.2019.112896

Beaumont, C., Makridakis, S., Wheelwright, S. C., & McGee, V. E. (1984). Forecasting: Methods and applications. The Journal of the Operational Research Society, 35(1), Article e79. https://doi.org/10.2307/2581936

Bilal, A. I., Bititci, U. S., & Fenta, T. G. (2024). Effective supply chain strategies in addressing demand and supply uncertainty: A case study of Ethiopian Pharmaceutical Supply Services. Pharmacy, 12(5), Article e132. https://doi.org/10.3390/pharmacy12050132

Brau, R. I., Sanders, N. R., Aloysius, J., & Williams, D. (2024). Utilizing people, analytics, and AI for decision making in the digitalized retail supply chain. Journal of Business Logistics, 45(1), Article e12355. https://doi.org/10.1111/jbl.12355

Calzone, O. (2022, February 21). An intuitive explanation of LSTM. Medium. https://medium.com/@ottaviocalzone/an-intuitive-explanation-of-lstm-a035eb6ab42c

Chen, H., Chiang, H. L., & Storey, V. C. (2012). Business Intelligence and Analytics: From Big Data to Big Impact. MIS Quarterly, 36(4), 1165–1188. https://doi.org/10.2307/41703503

Cherepovitsyn, A., Mekerova, I., & Nevolin, A. (2025). Analysis of the Palladium Market: A Strategic Aspect of Sustainable Development. Mining, 5(3), Article e39. https://doi.org/10.3390/mining5030039

Cui, R., Lu, Z., Sun, T., & Golden, J. M. (2024). Sooner or later? Promising delivery speed in online retail. Manufacturing & Service Operations Management, 26(1), 233–251. https://doi.org/10.1287/msom.2021.0174

De Almeida, F. M., Martins, A. M., Nunes, M. A., & Bezerra, L. C. T. (2022, June 15–16). Retail sales forecasting for a Brazilian supermarket chain: An empirical assessment [Paper presentation]. Proceedings of IEEE 24th Conference on Business Informatics (CBI), Amsterdam, Netherlands. https://doi.org/10.1109/CBI54897.2022.00014

Eberhart, R., & Kennedy, J. (1995, October 4–6). A new optimizer using particle swarm theory [Paper presentation]. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, Nagoya, Japan.

El-Adly, M. I., & Eid, R. (2016). An empirical study of the relationship between shopping environment, customer perceived value, satisfaction, and loyalty in the UAE malls context. Journal of Retailing and Consumer Services, 31, 217–227. https://doi.org/10.1016/j.jretconser.2016.04.002

Elsayed, S., Thyssens, D., Rashed, A., Jomaa, H. S., & Schmidt-Thieme, L. (2021). Do we really need deep learning models for time series forecasting? Cornell University. https:/doi.org/10.48550/arXiv.2101.02118

Fildes, R., Ma, S., & Kolassa, S. (2022). Retail forecasting: Research and practice. International Journal of Forecasting, 38(4), 1283–1318. https://doi.org/10.1016/j.ijforecast.2019.06.004

Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054

George, E. P. B., & Gwilym, M. J. (1970). Time series analysis: Forecasting and control. Holden-Day.

Haselbeck, F., Killinger, J., Menrad, K., Hannus, T., & Grimm, D. G. (2022). Machine learning outperforms classical forecasting on horticultural sales predictions. Machine Learning with Applications, 7, Article e100239. https://doi.org/10.1016/j.mlwa.2021.100239

He, Q.-Q., Wu, C., & Si, Y.-W. (2022). LSTM with particle Swam optimization for sales forecasting. Electronic Commerce Research and Applications, 51, Article e101118. https://doi.org/10.1016/j.elerap.2022.101118

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735

Islam, M. M. (2023). ECommerce data analysis. https://www.kaggle.com/datasets/mmohaiminulislam/ecommerce-data-analysis?

Kholod, M., Celani, A., & Ciaramella, G. (2024). The analysis of customers’ transactions based on POS and RFID data using big data analytics tools in the retail space of the future. Applied Sciences, 14(24), Article e11567. https://doi.org/10.3390/app142411567

Kitchens, B., Dobolyi, D., Li, J., & Abbasi, A. (2018). Advanced customer analytics: Strategic value through integration of relationship-oriented big data. Journal of Management Information Systems, 35(2), 540–574. https://doi.org/10.1080/07421222.2018.1451957

Kolassa, S. (2022). Commentary on the M5 forecasting competition. International Journal of Forecasting, 38(4), 1562–1568. https://doi.org/10.1016/j.ijforecast.2021.08.006

Kumar, S., & Mahapatra, R. P. (2021). Design of multi-warehouse inventory model for an optimal replenishment policy using a rain optimization algorithm. Knowledge-Based Systems, 231, Article e107406. https://doi.org/10.1016/j.knosys.2021.107406

Kumar, V., & Venkatesan, R. (2021). Transformation of metrics and analytics in retailing: The way forward. Journal of Retailing, 97, 496–506. https://doi.org/10.1016/j.jretai.2021.11.004

Kunz, W. H., & Wirtz, J. (2024). Corporate digital responsibility (CDR) in the age of AI: implications for interactive marketing. Journal of Research in Interactive Marketing, 18(1), 31–37. https://doi.org/10.1108/JRIM-06-2023-0176

Lens, V., Bushman-Copp, L., & Wimer, C. (2024). Fostering Financial and Family Well-Being: A Qualitative Study on How Parents Utilized the Expanded Child Tax Credit. Journal of Poverty. Advance online publication. https://doi.org/10.1080/10875549.2024.2379761

Liu, S., Liao, G., & Ding, Y. (2018, 31 May– 2 June). Stock transaction prediction modeling and analysis based on LSTM [Paper presentation]. Proceedings of 13th IEEE Conference on Industrial Electronics and Applications, Wuhan, China. https://doi.org/10.1109/ICIEA.2018.8398183

Macas, C. V. M., Aguirre, J. A. E., Arcentales-Carrión, R., & Peña, M. (2021, March 23–25). Inventory management for retail companies: A literature review and current trends [Paper presentation]. Proceedings of Second International Conference on Information Systems and Software Technologies, Quito, Ecuador.

Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018). Statistical and Machine Learning forecasting methods: Concerns and ways forward. PLOS ONE, 13(3), Article e0194889. https://doi.org/10.1371/journal.pone.0194889

Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022). The M5 competition: Background, organization, and implementation. International Journal of Forecasting, 38(4), 1325–1336. https://doi.org/10.1016/j.ijforecast.2021.07.007

Mustapha, O. O., & Sithole, T. (2025). Forecasting Retail Sales using Machine Learning Models. American Journal of Statistics and Actuarial Sciences, 6(1), 35–67. http://dx.doi.org/10.47672/ajsas.2679

Nordin, F., & Ravald, A. (2023). The making of marketing decisions in modern marketing environments. Journal of Business Research, 162, Article e113872. https://doi.org/10.1016/j.jbusres.2023.113872

Ramos, P., Santos, N., & Rebelo, R. (2015). Performance of state space and ARIMA models for consumer retail sales forecasting. Robotics and Computer-Integrated Manufacturing, 34, 151–163. https://doi.org/10.1016/j.rcim.2014.12.015

Rana, M. E., Yao, T. W., & Hameed, V. A. (2023). Optimizing sales forecasting: Implementing a deep learning model for accurate and timely predictions [Paper presentation]. Proceedings of 6th International Conference on Big Data and Artificial Intelligence, Jiaxing, China. https://doi.org/10.1109/BDAI59165.2023.10256821

Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning : A systematic literature review: 2005–2019. Applied Soft Computing, 90, Article e106181. https://doi.org/10.1016/j.asoc.2020.106181

Shao, B., Li, M., Zhao, Y., & Bian, G. (2019). Nickel price forecast based on the LSTM neural network optimized by the improved PSO Algorithm. Mathematical Problems in Engineering, 2019(1), Article e1934796. https://doi.org/10.1155/2019/1934796

Shultz, C., Hoek, J., Lee, L., Leong, W. Y., Srinivasan, R., Viswanathan, M., & Wertenbroch, K. (2022). JPP&M's global perspective and impact: An agenda for research on marketing and public policy. Journal of Public Policy & Marketing, 41(1), 34–50. https://doi.org/10.1177/07439156211049216

Soori, M., Arezoo, B., & Dastres, R. (2023). Artificial intelligence, machine learning and deep learning in advanced robotics, a review. Cognitive Robotics, 3, 54–70. https://doi.org/10.1016/j.cogr.2023.04.001

Stanelytė, G. (2021). Inventory optimization in retail network by creating a demand prediction model [Doctoral dissertation, Vilniaus Gedimino Technikos Universitetas]. eLABa. https://gs.elaba.lt/object/elaba:80509157/index.html

Wang, F., & Aviles, J. (2023). Enhancing operational efficiency: Integrating machine learning predictive capabilities in business intellgence for informed decision-making. Frontiers in Business, Economics and Management, 9(1), 282–286.

Wang, J., Liu, G. Q., & Liu, L. (2019, March 15–18). A selection of advanced technologies for demand forecasting in the retail industry [Paper presentation]. Proceedings of 4th International Conference on Big Data Analytics, Suzhou, China. https://doi.org/10.1109/ICBDA.2019.8713196

Yan, K., & Deng, D. (2024). Research on supermarket replenishment volume prediction based on LSTM and PSO algorithm. Journal of Education, Humanities and Social Sciences, 25, 129–137. https://doi.org/10.54097/e8w01s21

Yan, S., Archibald, T. W., Han, X., & Bian, Y. (2022). Whether to adopt “buy online and return to store” strategy in a competitive market? European Journal of Operational Research, 301(3), 974–986. https://doi.org/10.1016/j.ejor.2021.11.040

Yu, H. (2023). Pop-up retail strategies in an omnichannel context.

Zeroual, A., Harrou, F., Dairi, A., & Sun, Y. (2020). Deep learning methods for forecasting COVID-19 time-Series data: A comparative study. Chaos, Solitons & Fractals, 140, Article e110121. https://doi.org/10.1016/j.chaos.2020.110121