COMPARISON OF MACHINE LEARNING MODELS FOR FORECASTING RETAIL SALES IN THAILAND
Article Sidebar
Main Article Content
Abstract
This research focuses on analyzing the efficiency of the model in forecasting retail sales in Thailand. It enables the forecast results to be effectively applied to business strategy planning that leads to important guidelines for researchers and entrepreneurs in selecting the most efficient forecasting model using the Long Short-Term Memory, Gradient Boosting Machines and Random Forest models. The work process is divided into 4 parts. Part 1: Data collection, Part 2: Data cleaning, Part 3: Data analysis, and Part 4: Model evaluation. This work uses data from the Data.go.th database, which contains 7 attributes and 50,219 rows. The results of the research have revealed that the evaluation of the efficiency of the model used in forecasting retail sales in Thailand with the highest efficiency is LSTM, which can indicate the most accurate forecasting ability with an R-squared value of 0.90. Importantly, LSTM is recognized as the most efficient in predicting retail sales. The second place is GBM which can indicate accurate forecasting efficiency with an R-squared value of 0.89 and the third place is RF which can indicate accurate forecasting efficiency with an R-squared value of 0.88, respectively.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
I and co-author(s) certify that articles of this proposal had not yet been published and is not in the process of publication in journals or other published sources. I and co-author accept the rules of the manuscript consideration. Both agree that the editors have the right to consider and make recommendations to the appropriate source. With this rights offering articles that have been published to Panyapiwat Institute of Management. If there is a claim of copyright infringement on the part of the text or graphics that appear in the article. I and co-author(s) agree on sole responsibility.
References
Alpaydin, E. (2020). Introduction to machine learning. The MIT Press.
Badmus, O., Rajput, S. A., Arogundade, J. B., & Williams, M. (2024). AI-driven business analytics and decision making. World Journal of Advanced Research and Reviews, 24(1), 616-633.
Central Retail Corporation. (2023). Thailand’s omnichannel shopping trends in the fashion industry. https://www.centralretail.com/en/investor-relations/document/annual-reports [in Thai]
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794). The Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785
DataTechNotes. (2019). Regression model accuracy (MAE, MSE, RMSE, R-squared) check in R. https://www.datatechnotes.com [in Thai]
Elahi, M., Afolaranmi, S. O., Martinez Lastra, J. L., & Perez Garcia, J. A. (2023). A comprehensive literature review of the applications of AI techniques through the lifecycle of industrial equipment. Discover Artificial Intelligence, 3(1), 43.
Euromonitor International. (2024). Thailand retail and safety 2024. https://www.euromonitor.com [in Thai]
Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2017). LSTM: A search space odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10), 2222-2232.
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and practice (3rd ed.). OTexts.
Fildes, R., & Petropoulos, F. (2015). Simple versus complex selection rules for forecasting many time series. Journal of Business Research, 68(8), 1692-1701.
Fildes, R., Ma, S., & Kolassa, S. (2022). Retail forecasting: Research and practice. International Journal of Forecasting, 38(4), 1283-1318.
Krungsri Bank. (2024). Trends in business/industry 2024-2026: Modern retail business. https://www.krungsri.com/th/research/industry/industry-outlook/wholesale-retail/modern-trade/io/modern-trade-2024-2026 [in Thai]
Lakshmanan, B., Vivek Raja, P. S. N., & Kalathiappan, V. (2020). Sales demand forecasting using LSTM network. In Artificial Intelligence and evolutionary computations in engineering systems (pp. 125-132). Springer.
Ma, S., & Fildes, R. (2021). Retail sales forecasting with meta-learning. European Journal of Operational Research, 288(1), 111-128.
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2020). The M4 competition: 100,000 time series and 61 forecasting methods. International Journal of Forecasting, 36(1), 54-74.
McKinsey & Company. (2023). Retail reset: A new guide for retail leaders. https://www.mckinsey.com [in Thai]
Montgomery, D. C., Peck, E. A., & Vining, G. G. (2012). Introduction to linear regression analysis (5th ed.). Wiley.
Mordor Intelligence. (2023). Thailand retail industry-outlook, size & market analysis. https://www.mordorintelligence.com
Nasseri, M., Falatouri, T., Brandtner, P., & Darbanian, F. (2023). Applying machine learning in retail demand prediction—A comparison of tree-based ensembles and long short-term memory-based deep learning. Applied Sciences (Switzerland), 13(19), 12-32.
Oukassi, H., Hasni, M., & Layeb, S. B. (2023). Long short-term memory networks for forecasting demand in the case of automotive manufacturing industry. In 2023 IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET) (pp. 1-6). IEEE.
Ren, S., Chan, H. L., & Siqin, T. (2020). Demand forecasting in retail operations for fashionable products: Methods, practices, and real case study. Annals of Operations Research, 291, 761-777.
Rodriguez-Galiano, V. F., Ghimire, B., Rogan, J., Chica-Olmo, M., & Rigol-Sanchez, J. P. (2012). An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67, 93-104.
Seshan, S., Vries, D., Immink, J., Helm, A. van der, & Poinapen, J. (2024). LSTM-based autoencoder models for real-time quality control of wastewater treatment sensor data. Journal of Hydroinformatics, 26(2), 441-458.
Shihe, R., Hui, W., & Na, L. (2015). Review of ocean front in Chinese marginal seas and frontal forecasting. Advances in Earth Science, 30(5), 552.
Wellens, A. P., Boute, R. N., & Udenio, M. (2024). Simplifying tree-based methods for retail sales forecasting with explanatory variables. European Journal of Operational Research, 314(2), 523-539.
Wolpert, D. H., & Macready, W. G. (1997). No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation, 1(1), 67-82.
