A Machine Learning-Based Stock Forecasting Method for Inventory Optimization in Micro and Small Enterprises
Received: 15 October 2025 | Revised: 17 November 2025 and 1 December 2025 | Accepted: 3 December 2025 | Online: 9 February 2026
Corresponding author: Juan Mansilla-Lopez
Abstract
Efficient inventory management remains a critical challenge for Micro and Small Enterprises (MSEs) that operate under limited resources and fluctuating market demands. This study proposes a lightweight and interpretable machine-learning framework based on the Random Forest algorithm to predict product demand and optimize inventory levels. Historical sales data was preprocessed, structured, and used to train and validate the model through multiple evaluation metrics. The proposed model achieved a Mean Absolute Percentage Error (MAPE) of 2.41% and a Coefficient of Determination (R²) of 0.99, outperforming comparative models such as K-Nearest Neighbors, Decision Tree, and XGBoost. These results confirm the model's capacity to capture short-term fluctuations and long-term trends with high predictive accuracy. Feature-importance analysis revealed that the interaction between quantity and price was the most influential variable, followed by relative price and seasonal factors. The findings demonstrate that data-driven forecasting can significantly reduce overstocking and stockout situations, enhancing operational efficiency and decision-making. This study establishes a reproducible, resource-efficient forecasting workflow tailored specifically to the operational constraints of MSEs, filling an existing methodological gap in inventory prediction research.
Keywords:
inventory management, machine learning, stock prediction, MSEs, demand forecasting, desktop applicationDownloads
References
M. Ghazi, H. S. Salih, and M. Aljanabi, "Implementing an Automated Inventory Management System for Small and Medium-sized Enterprises," Iraqi Journal for Computer Science and Mathematics, pp. 238–244, May 2023. DOI: https://doi.org/10.52866/ijcsm.2023.02.02.021
M. Kim, J. Lee, C. Lee, and J. Jeong, "Framework of 2D KDE and LSTM-Based Forecasting for Cost-Effective Inventory Management in Smart Manufacturing," Applied Sciences, vol. 12, no. 5, Feb. 2022, Art. no. 2380. DOI: https://doi.org/10.3390/app12052380
M. Arampatzis, M. Pempetzoglou, and A. Tsadiras, "Two Lot-Sizing Algorithms for Minimizing Inventory Cost and Their Software Implementation," Information, vol. 15, no. 3, Mar. 2024, Art. no. 167. DOI: https://doi.org/10.3390/info15030167
W. Yang, Y. Chen, Y. C. Chen, and K. C. Yeh, "Intelligent Agent-Based Predict System With Cloud Computing for Enterprise Service Platform in IoT Environment," IEEE Access, vol. 9, pp. 11843–11871, 2021. DOI: https://doi.org/10.1109/ACCESS.2021.3049256
D. Cica, B. Sredanovic, S. Tesic, and D. Kramar, "Predictive modeling of turning operations under different cooling/lubricating conditions for sustainable manufacturing with machine learning techniques," Applied Computing and Informatics, Aug. 2020. DOI: https://doi.org/10.1016/j.aci.2020.02.001
P. Raghuram, B. S, R. Manivannan, P. S. P. Anand, and V. R. Sreedharan, "Modeling and Analyzing the Inventory Level for Demand Uncertainty in the VUCA World: Evidence From Biomedical Manufacturer," IEEE Transactions on Engineering Management, vol. 70, no. 8, pp. 2944–2954, Aug. 2023. DOI: https://doi.org/10.1109/TEM.2022.3201440
Y. Rothacher and C. Strobl, "Identifying Informative Predictor Variables With Random Forests," Journal of Educational and Behavioral Statistics, vol. 49, no. 4, pp. 595–629, Aug. 2024. DOI: https://doi.org/10.3102/10769986231193327
E. I. Altman, M. Balzano, A. Giannozzi, and S. Srhoj, "Revisiting SME default predictors: The Omega Score," Journal of Small Business Management, vol. 61, no. 6, pp. 2383–2417, Nov. 2023. DOI: https://doi.org/10.1080/00472778.2022.2135718
B. B. Hojnik and I. Huđek, "Small and Medium-Sized Enterprises in the Digital Age: Understanding Characteristics and Essential Demands," Information, vol. 14, no. 11, Nov. 2023, Art. no. 606. DOI: https://doi.org/10.3390/info14110606
V. Vadi, A. Kotadiya, R. Solanki, and M. M. Khambalkar, "Low-Cost Asset Tracking and Inventory Management System (ATIM)," Journal of Physics: Conference Series, vol. 2007, no. 1, Aug. 2021, Art. no. 012072. DOI: https://doi.org/10.1088/1742-6596/2007/1/012072
W. Chen, J. Childs, S. Ray, B. S. Lee, and T. Xia, "RFID Technology Study for Traffic Signage Inventory Management Application," IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 10, pp. 17809–17818, Oct. 2022. DOI: https://doi.org/10.1109/TITS.2022.3164579
M. Feurer et al., "OpenML-Python: an extensible Python API for OpenML," Journal of Machine Learning Research, vol. 22, no. 100, pp. 1–5, 2021.
A. Kallmuenzer, A. Mikhaylov, M. Chelaru, and W. Czakon, "Adoption and performance outcome of digitalization in small and medium-sized enterprises," Review of Managerial Science, vol. 19, no. 7, pp. 2011–2038, July 2025. DOI: https://doi.org/10.1007/s11846-024-00744-2
B. B. Tyler et al., "Environmental practice adoption in SMEs: The effects of firm proactive orientation and regulatory pressure," Journal of Small Business Management, vol. 62, no. 5, pp. 2211–2246, Sept. 2024. DOI: https://doi.org/10.1080/00472778.2023.2218435
N. E. I. Karabadji, A. Amara Korba, A. Assi, H. Seridi, S. Aridhi, and W. Dhifli, "Accuracy and diversity-aware multi-objective approach for random forest construction," Expert Systems with Applications, vol. 225, Sept. 2023, Art. no. 120138. DOI: https://doi.org/10.1016/j.eswa.2023.120138
E. Rivandi and R. J. Oskouei, "A Novel Approach for Developing Intrusion Detection Systems in Mobile Social Networks," Journal of Soft Computing and Decision Analytics, vol. 3, no. 1, pp. 158–170, Oct. 2025. DOI: https://doi.org/10.31181/jscda31202576
P. Nikzat and S. Hosseinzade, "A Practical Model to Measure E-Service Quality and E-Customer Satisfaction of Crypto Wallets," Open Journal of Business and Management, vol. 13, no. 03, pp. 1634–1660, 2025. DOI: https://doi.org/10.4236/ojbm.2025.133085
A. Pezeshgi, M. Naeimi, and Q. Family, "Buying on Impulse in the Age of AI: Mechanisms, Evidence, and Moral Dilemmas." Social Science Research Network, Rochester, NY, Aug. 07, 2025. DOI: https://doi.org/10.2139/ssrn.5402344
M. S. Karizaki, D. Gnesdilow, S. Puntambekar, and R. J. Passonneau, "How Well Can You Articulate that Idea? Insights from Automated Formative Assessment." arXiv, Apr. 17, 2024. DOI: https://doi.org/10.1007/978-3-031-64299-9_16
S. Sanaei, M. Manna, H. Bozorgkhou, S. Heidari, and E. Mehregan, "The Role of SCM practices inCompetitive Advantage and Firm Performance: A Mediating Role of Supply ChainInnovation and TQM," Tehnički glasnik, vol. 17, no. 4, pp. 516–523, Oct. 2023. DOI: https://doi.org/10.31803/tg-20221223200658
M. B. Bagherabad, E. Rivandi, and M. J. Mehr, "Machine Learning for Analyzing Effects of Various Factors on Business Economic." TechRxiv, Apr. 10, 2025. DOI: https://doi.org/10.36227/techrxiv.174429010.09842200/v1
Y. Saremi, M. Aghaei, M. R. Esfid, T. Hasangholipour, and M. Ansari, "Providing Digital Marketing Model with Customer Participation Approach with intervening role of knowledge management," International Journal of Knowledge Processing Studies, vol. 4, no. 2, Mar. 2024.
V. Ladva, M. Shukla, and C. Vaghela, "The Impact of Supply Chain Delays on Inventory Levels and Sale Demand Fulfillment: Analyzing the Effects of Lead Times and In-Transit Quantities: A Quantitative Exploration of Logistics Efficiency and Inventory Optimization," Engineering, Technology & Applied Science Research, vol. 14, no. 4, pp. 15700–15710, Aug. 2024. DOI: https://doi.org/10.48084/etasr.7834
Downloads
How to Cite
License
Copyright (c) 2025 Jimmy K. Franco, Nelson M. Guevara, Pedro Castaneda, Juan Mansilla-Lopez, Alberto Daniel Garcia-Nunez
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
