ShelfMind: Demand Forecasting and Stock Control for Retail SMEs using Global XGBoost and Context-Injected AI Chatbot
- Aulia Syafitri Politeknik Negeri Sriwijaya, Palembang, Indonesia
-
Aryanti Aryanti
*
Politeknik Negeri Sriwijaya, Palembang,
Indonesia
- Sholihin Sholihin Politeknik Negeri Sriwijaya, Palembang, Indonesia (*) Corresponding Author
Abstract
SME retail stores in Indonesia face serious challenges in inventory management: stockouts of popular products, waste from perishable items that expire before being sold, and restocking decisions relying on owner intuition. This research develops ShelfMind, a web-based inventory management system integrating three main components: a demand prediction model using a global XGBoost algorithm, an AI chatbot based on real-time data context injection, and an active notification system for low-stock and expiry risk alerts. Dataset from Toko Tika Baru covered 47 products in 11 categories with 8,225 daily sales records over 205 days. The XGBoost model was trained with 29 time-engineered features and achieved an MAE of 0.4107 units/day and RMSE of 0.5081 units/day on a 40-day test set. The global XGBoost method and context injection approach were selected due to their computational efficiency, avoiding the high costs associated with LLM fine-tuning, thus making it an ideal solution for SMEs with limited budget and infrastructure data. The AI chatbot, using context injection from inventory, sales, and XGBoost forecast data, achieved an average relevance and data accuracy of 4.94/5 across 20 test scenarios with an average response time of 2.94 seconds. Black-box functional testing of 31 scenarios passed completely. Usability evaluation scored 3.77/5, with notes on improving the communication of prediction features to non-technical users. This system proves that integrating XGBoost and LLM in an SME inventory management platform is technically feasible and provides tangible value for retail operations.
Downloads
References
M. Elorza, E. Castellano, and S. Segura, “Prediction of customer demand for perishable products in retail inventory management, using the hybrid prophet-XGBoost model during the post-COVID-19 period,” Appl. Econ. Lett., vol. 32, no. 17, pp. 2453–2459, 2025, [Online]. Available: https://doi.org/10.1080/13504851.2024.2333995
R. Naznin et al., “Enhancing small business management through machine learning: A comparative study of predictive models for customer retention, financial forecasting, and inventory optimization,” Int. Interdiscip. Bus. Econ. Adv. J., vol. 5, no. 11, pp. 21–32, 2024, [Online]. Available: https://doi.org/10.55640/business/volume05issue11-03%0A
J. Loa, J. Wiratama, and F. A. Halim, “Optimizing Inventory Management in Retail Companies Through Sales Prediction Using XGBoost,” in 2025 4th International Conference on Electronics Representation and Algorithm (ICERA), IEEE, 2025, pp. 1–6. doi: 10.1109/ICERA66156.2025.11087347.
S. Esmailizade, A. Ebrahimi, H. Soltani, A. Sam, and M. Rahimi, “Machine Learning Approaches for Retail Forecasting: A Study on XGBoost and Time-Series Models,” 2024, Authorea.
M. M. Hameed, A. Masood, A. Hamid, A. Elbeltagi, S. F. M. Razali, and A. Salem, “Forecasting monthly runoff in a glacierized catchment: a comparison of extreme gradient boosting (XGBoost) and deep learning models,” PLoS One, vol. 20, no. 5, p. e0321008, 2025, doi: 10.1371/journal.pone.0321008.
H. Abdelsalam, A. Souri, and N. İnanç, “A time series forecasting approach based on gradient boosting method for IoT-based solar energy production systems,” Energy Storage Sav., vol. 4, no. 4, pp. 413–420, 2025, doi: doi.org/10.1016/j.enss.2025.04.003.
V. Khatri and N. Trivedi, “LLM Chatbot Integration With Inventory Systems for Gastroenterology and Endoscopy Services: A Systematic Review,” J. Eval. Clin. Pract. homepage, vol. 32, no. 4, 2026, doi: doi.org/10.1111/jep.70478.
D. I. Purnamasari, V. A. Permadi, A. Saepudin, and R. P. Agusdin, “Demand Forecasting for Improved Inventory Management in Small and Medium-Sized Businesses,” J. Nas. Pendidik. Tek. Inform., vol. 12, no. 1, pp. 56–66, 2023, [Online]. Available: https://doi.org/10.23887/janapati.v12i1.57144
M. Kmiecik, “Supporting the Inventory Management in the Manufacturing Company by ChatGPT,” Manag. Prod. Eng. Rev., vol. 19, no. 4, pp. 535–554, 2023, [Online]. Available: http://doi.org/10.17270/J.LOG.2023.917 Received:
M. Kavitha, R. Srinivasan, R. Kavitha, and M. Suganthy, Sales Demand Forecasting for Retail Marketing Using XGBoost Algorithm. USA: Wiley, 2023. doi: 10.1002/9781394167524.ch9.
B. Wang and A. B. M. Zain, “A Hybrid XGBoost-LSTM Framework for Supply Chain Demand Forecasting: Empirical Evidence from Retail Multi-Store Data,” J. Cult. Anal. Soc. Chang., vol. 10, no. 4, pp. 4056–4073, 2025, doi: doi.org/10.64753/jcasc.v10i4.3736.
J. Berryman and A. Ziegle, “Prompt Engineering for LLMs: The Art and Science of Building Large Language Model–Based Applications. O’Reilly Media,” USA: O’Reilly Media, 2024, pp. 280–282. [Online]. Available: https://books.google.com/books?id=9EQvEQAAQBAJ
D. I. Adelani et al., “MasakhaNER: Named entity recognition for African languages,” Trans. Assoc. Comput. Linguist., vol. 9, no. 10, pp. 1116–1131, 2021, doi: doi.org/10.1162/tacl_a_00416.
N. Cabanos, W. Le, and A. Ghassemi, “An Empirical Analysis of NLP-Based Databases for Inventory Management,” IEEE Access, vol. 1, no. 9, 2026, [Online]. Available: doi:10.1109/ICJECE.2025.3638759
B. Arugula, “Prompt engineering for LLMs: Real-world applications in banking and ecommerce,” Int. J. Artif. Intell. Data Sci. Mach. Learn., vol. 6, no. 1, pp. 115–123, 2025, doi: doi.org/10.63282/3050-9262.IJAIDSML-V6I1P113.
S. Ayad and F. Alsayoud, “Prompt engineering techniques for semantic enhancement in business process models,” Bus. Process Manag. J., vol. 30, no. 7, pp. 2611–2461, 2024, doi: doi.org/10.1108/BPMJ-02-2024-0108.
Z. Xu, M. J. Cruz, and X. Wang, Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering, vol. 1, no. 1. Association for Computing Machinery, 2024. doi: 10.1145/3626772.3661370.
W. Meng, Y. Li, L. Chen, and Z. Dong, “Using the retrieval-augmented generation to improve the question-answering system in human health risk assessment: the development and application,” Electronics, vol. 14, no. 2, p. 386, 2025, doi: 10.3390/electronics14020386.
O. Çaylı and Z. Oralhan, “Artificial intelligence-driven inventory management: Optimizing stock levels and reducing costs through advanced machine learning techniques,” Eur. J. Res. Dev., vol. 4, no. 4, pp. 427–439, 2024, doi: 10.56038/ejrnd.v4i4.615.
R. Tatikonda, M. Kempanna, R. Thatikonda, A. Bhuvanesh, R. Thota, and R. Keerthanadevi, “Chatbot and its Impact on the Retail Industry,” in 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), Bengaluru, India, India: IEEE (Conference Proceedings), 2025, pp. 2084–2089. doi: 10.1109/IDCIOT64235.2025.10915098.
A. D. Hartanto, Y. N. Kholik, and Y. Pristyanto, “Stock price time series data forecasting using the light gradient boosting machine (LightGBM) model,” JOIV Int. J. Informatics Vis., vol. 7, no. 4, pp. 2270–2279, 2023, doi: dx.doi.org/10.62527/joiv.7.4.1740.
S. Makridakis, E. Spiliotis, and V. Assimakopoulos, “M5 accuracy competition : Results , findings , and conclusions,” Int. J. Forecast., vol. 38, no. 4, pp. 1346–1364, 2022, doi: 10.1016/j.ijforecast.2021.11.013.
M. Steve, S. Brightwood, and O. Godwin, “Implementing AI Chatbots for Real-Time Supply Chain Monitoring and Risk Management,” 2024. [Online]. Available: https://www.researchgate.net/publication/383395365
L.-C. Chen, H.-T. Weng, M. S. Pardeshi, C.-M. Chen, R.-K. Sheu, and K.-C. Pai, “Evaluation of prompt engineering on the performance of a large language model in document information extraction,” Electronics, vol. 14, no. 11, p. 2145, 2025, doi: 10.3390/electronics14112145.
H. J. Wahedi, M. Heltoft, G. J. Christophersen, T. Severinsen, S. Saha, and I. E. Nielsen, “Forecasting and inventory planning: An empirical investigation of classical and machine learning approaches for svanehøj’s future software consolidation,” Appl. Sci., vol. 13, no. 15, p. 8581, 2023, doi: 10.3390/app13158581.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel ShelfMind: Demand Forecasting and Stock Control for Retail SMEs using Global XGBoost and Context-Injected AI Chatbot
Pages: 439-449
Copyright (c) 2026 Aulia Syafitri, Aryanti Aryanti, Sholihin Sholihin
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 copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment 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 acknowledgment 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
