From Reactive to Proactive Governance: A Hybrid LSTM–Gradient Boosting Architecture for Real-Time Anomaly Signal Detection in Multi-Store Retail Supply Chain Decision Systems
Keywords:
supply chain risk governance, hybrid deep learning, LSTM, gradient boosting, real-time anomaly detection, retail time-series forecasting, interpretable AI, proactive decision systems.Abstract
Contemporary multi-store retail supply chains operate under intensifying volatility driven by promotional dynamics, macroeconomic shocks, and exogenous disruptions yet most decision-support systems remain anchored in reactive, lagging indicators. This study introduces a novel hybrid deep learning architecture that synergistically integrates Long Short-Term Memory (LSTM) networks for temporal dependency modeling with Gradient Boosting Machines (GBM) for high-dimensional feature interaction capture, enabling real-time detection of latent risk signals within store-level sales trajectories. Leveraging the publicly available Store Sales Time Series Forecasting dataset (Kaggle, 2022), comprising 54 Ecuadorian retail outlets, 3,000+ product families, and auxiliary covariates including oil prices, national holidays, and promotional intensity, we demonstrate that our stacked ensemble framework achieves superior early-warning capability compared to standalone LSTM, XGBoost, or ARIMA benchmarks. Critically, the architecture embeds a probabilistic calibration layer (Platt scaling) and SHAP-based interpretability module, transforming opaque risk scores into actionable procurement narratives for supply chain managers. Results indicate a 23.7% reduction in false-negative anomaly detection and a 15.2% improvement in lead-time for intervention signals, advancing the paradigm from post-hoc correction to anticipatory governance. The methodological contribution lies not merely in predictive accuracy, but in establishing a reproducible, auditable framework for embedding AI-driven risk intelligence within operational decision loops addressing the accountability, drift, and escalation gaps identified in contemporary autonomous supply chain .
Downloads
References
1. Wang, B., & Zain, A. B. M. (2025). A Hybrid XGBoost-LSTM Framework for Supply Chain Demand Forecasting: Empirical Evidence from Retail Multi-Store Data. Journal of Cultural Analysis and Social Change, 4056-4073.
2. Xiaoyang, C. (2025). Explainable dual LSTM-autoencoders with exogenous features for anomaly detection and supply chain forecasting. Scientific Reports, 15(1), 42371.
3. Mishra, H., Sharma, G., Sharma, N., & Tripathi, A. (2026). AI-Based Predictive Waste Reduction System in Supermarkets: A Dashboard-Driven Approach. International Journal of Science and Technology (IJST), 3(2), 12-23.
4. Neti, K. (2025). Enhancing Product Supply Forecasting in the Presence of Returns in Retail Supply Chains Through Data-Driven Modeling (Master's thesis, State University of New York at Binghamton).
5. Sawalha, S. F. (2022). Towards a High-Speed Big Data Analytics Framework for IoT (Doctoral dissertation, Princess Sumaya University for Technology (Jordan)).
6. Ben Dalla, L. O. F., Medeni, T. D., Medeni, I. T., & Ulubay, M. (2025). Enhancing Healthcare Efficiency at Almasara Hospital: Distributed Data Analysis and Patient Risk Management. Economy: Strategy and Practice, 19(4), 54–72. https://doi.org/10.51176/1997-9967-2024-4-54-72
7. Gupta, A., & Remella, S. (2026). Deep Learning Models for Predicting Cyber Physical Attacks in Supply Chain Networks. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 7(1), 135-140.
8. Dalla, L. O. F. B. (2020). Modeling by using Generic Modeling Environment (GME) Domain specific modeling language (DSL) for agile software development (ASD) types.
9. Бен Далла Л., Медени Т.Д., Медени И.Т., Улубай М. Повышение эффективности здравоохранения в больнице Алмасара: анализ распределенных данных и управление рисками для пациентов. Economy: strategy and practice. 2024;19(4):54-72. https://doi.org/10.51176/1997-9967-2024-4-54-72
10. FARAJ, L. O. (2017). OBSERVATIONS ON EVOLUTION OF LEAN SOFTWARE DEVELOPMENT (LSD). 88 pages.https://tez.yok.gov.tr/UlusalTezMerkezi/tezDetay.jsp?id=R_EJxYiWWNffOuWM4F4eXQ&no=fiwArXgOvJPKmFC-nX3H-w
11. Dalla, L. O. F. B. (2020). IT security Cloud Computing. . In 2020 IT security Cloud Computing Applications Conference (ITSCC) (pp. 1-10). IEEE. https://doi.org/10.16377/ITSCC 50717.2020.9259880
12. Degirmenci, A., & Karal, O. (2022). iMCOD: Incremental multi-class outlier detection model in data streams. Knowledge-Based Systems, 258, 109950. https://doi.org/10.1016/j.knosys.2022.109950
13. Alsharif, A., Solman, F. I., Gheidan, A. A. S., Ahmed, A. A., Dalla, L. O. F. B., Alsharif, M. A., ... & Imbayah, I. (2026). Photovoltaic Cells: Principles of Operation and Performance Characteristics. Journal of Scientific and Human Dimensions, 718-748. https://doi.org/10.65421/jshd.v2i1.122
14. Alsharif, A., Ahmed, A. A., Musa, Z. A., Dalla, L. O. F. B., & Nouh, A. (2026). Drugs: The Path of Darkness Between Religious Awareness and Societal Loss. International Journal of Academic Publishing in Educational Sciences and Humanities (IJAPESH), 2(1), 49-56.
15. A-abdullatef, M. M., Albaraesi, M. J. S., EL-sseid, M. A. M., Dalla, L. O. B., Ahmed, A. A., Agila, A., & Alsharif, A. (2026). Tri-Conditional Biomechanical Signature Extraction: A Hybrid Framework Integrating Multivariate Functional Clustering, Cross-Modal Regression, and Inter-Subject Classification for Discriminative Gait Pattern Analysis. Comprehensive Science Journal, 10(39), 1063-1087. https://doi.org/10.65405/0j1byd74
16. Elghaffi, F. S. A. (2026). Temporal Dynamics in Intraoperative Monitoring: A Novel LSTM-Based Framework for Multivariate Time Series Classification in Critical Care Events. Temporal Dynamics in Intraoperative Monitoring: A Novel LSTM-Based Framework for Multivariate Time Series Classification in Critical Care Events. https://cjos.histr.edu.ly/index.php/journal
17. Elghaffi, F., Mohammed, O., Dalla, L., Ahmed, A., Agila, A., & EL-Sseid, M. (2026). Hybrid Matrix-Ensemble Framework for Chronic Kidney Disease Diagnosis. Wadi Alshatti University Journal of Pure and Applied Sciences, 4(1), 263-276. https://doi.org/10.63318/waujpasv4i1_28
18. DALLA, L. B. (2020). The Sustainable Efficiency of Modeling a Correspondence Undergraduate Transaction Framework by using Generic Modeling Environment (GME. Ben Dalla. International Journal of Engineering and Modern Technology E-ISSN 2504-8848 P-ISSN 2695-2149 . Vol 6 No 1 2020 www.iiardpub.org
19. Dalla, L. O. B., Karal, Ö., Degirmenci, A., EL-sseid, M. A. M., Essgaer, M., & Alsharif, A. (2025). A comprehensive literature review (LR) on optimization algorithms of sewage water treatment processes. Comprehensive Science Journal, 10(37), 3204-3220.
20. Dalla, L. O. F. B., & AHMAD, T. M. A. (2024). Integration of Artificial Bee Colony Algorithm with Deep Learning for Predictive Maintenance in Industrial IoT.
21. Ben Dalla, L., Medeni, T. M., Agila, A. A., & Medeni, İ. M. (2024). Architectural Synergy: Investigating the Role of Artificial Neural Networks in Enabling Deep Learning. The International Journal of Engineering & Information Technology (IJEIT), 12(1), 96-103.
22. Ramadhan, H. R. S., Osman, M. O. M., Dalla, L. O. F. B., Rashid, T. A., Albaraesi, M. J. S., El-Sseid, M. A. M., & Alnnale, T. (2025). A New Approach of the Machine Learning Framework Integrating Policy Design to Predict Renewable Electricity Penetration in Resource-Constrained Settings. Comprehensive Science Journal, 10(Supplement 38), 2929-2950
23. Albaraesi, M. J. S., Ali, M. A. M. A., Dalla, L. O. B., EL-sseid, M. A. M., Medeni, T. D., Medeni, İ. T., & Alnnale, T. (2025). Random construction in the city of Al-Bayda during the period 2011-2022 and its irregular expansion and its impact on the urban landscape. Comprehensive Science Journal, 10 (Supplement 38), 2590-2614.
24. A-abdullatef, M. M., Osman, M. O. M., Elghaffi, F. S. A., Dalla, L. O. B., Agila, A. A. A., & Alsharif, A. (2025). LATENT: Low-Latency Anomaly Tracking in National Electricity Time-Series Using Hybrid LSTM-Regression Architectures–A Case Study of Bangladesh’s PGCB Grid. Comprehensive Science Journal, 9(36), 1891-1912.
25. Jetlawei, S. S., Dalla, L. O. B., Karal, Ö., Degirmenci, A., El-Sseid, M. A. M., Essgaer, M., & Alsharif, A. (2025). Temporal Intelligence and Algorithmic Equity: A Multi-Phase Framework for Predictive Student Success in Higher Education. Comprehensive Science Journal, 9(36), 1574-1595.https://doi.org/10.65405/f0xx5p02
26. Dalla, L. O. F. B. (2020). Lean Software Development Practices and Principles in Terms of Observations and Evolution Methods to increase work environment productivity. International Journal of Engineering and Modern Technology, 6(1), 23-45.
27. Loganathan, K. A., & Chinnaraju, A. (2025). AI-Native Supply Chain Resilience: A Multimodal Architecture for Predictive Intelligence, Optimization, and Real-Time Decision-Making.
28. Dalla, L. O. F. B., & AHMAD, T. M. A. (2024). IMPROVE DYNAMIC DELIVERY SERVICES USING ANT COLONY OPTIMIZATION ALGORITHM IN THE MODERN CITY BY USING PYTHON RAY FRAMEWORK.
29. Karal, Ö. (2020). Performance comparison of different kernel functions in SVM for different k value in k-fold cross-validation. In 2020 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 1-5). IEEE. https://doi.org/10.1109/ASYU50717.2020.9259880
30. Ben Dalla, L., Medeni, T. M., Zbeida, S. Z., & Medeni, İ. M. (2024). Unveiling the Evolutionary Journey based on Tracing the Historical Relationship between Artificial Neural Networks and Deep Learning. The International Journal of Engineering & Information Technology (IJEIT), 12(1), 104-110.
31. Dalla, L. O. F. B. (2020). Lean Software Development Practices and Principles in Terms of Observations and Evolution Methods to increase work environment productivity.
32. Qin, Z., Luo, Q., Nong, X., Chen, X., Zhang, H., & Wong, C. U. I. (2025). Mas-lstm: A multi-agent lstm-based approach for scalable anomaly detection in iiot networks. Processes, 13(3), 753.
33. Ben Dalla, L., MEDENİ, T., MEDENİ, İ., & ULUBAY, M. (2024). Enhancing Healthcare Efficiency at Almasara Hospital: Distributed Data Analysis and Patient Risk Management. Economy: strategy and practice, 19(4).
34. Li, H. (2026). Sensor-driven AI Framework for Sustainable Agri-food Supply Chain: Policy Gradient Optimization with IoT and Twin Delayed Deep Deterministic Policy Gradient Algorithm. Sensors and Materials, 38(3), 1537-1551.
35. BEN, D. L., MEDENI, T., MEDENI, I., & ULUBAY, M. (2024). ENHANCING HEALTHCARE EFFICIENCY AT ALMASARA HOSPITAL: DISTRIBUTED DATA ANALYSIS AND PATIENT RISK MANAGEMENT. ЭКОНОМИКА, 19(4), 54-72.
36. Sattar, M. U., Dattana, V., Hasan, R., Mahmood, S., Khan, H. W., & Hussain, S. (2025). Enhancing supply chain management: A comparative study of machine learning techniques with cost–accuracy and ESG-based evaluation for forecasting and risk mitigation. Sustainability, 17(13), 5772.
37. Ben Dalla, L., Medeni, T. M., Agila, A. A., & Medeni, İ. M. (2024). Architectural Synergy: Investigating the Role of Artificial Neural Networks in Enabling Deep Learning. The International Journal of Engineering & Information Technology (IJEIT), 12(1), 96-103.
38. Dalla, L. O. F. B. (2020). The Influence of hospital management framework by the usage of Electronic healthcare record to avoid risk management (Department of Communicable Diseases at Misurata Teaching Hospital: Case study). EHRM, 20(4), 22–52. https://doi.org/20.51176/1954-9923-2020-4-22-52
39. James, U. U. (2022). Machine learning-driven anomaly detection for supply chain integrity in 5G industrial automation systems. International Journal of Scientific Research in Science, Engineering and Technology, 9(2), 2017-2023.
40. Dalla, L. O. F. B. (2020). Dorsal Hand Vein (DHV) Verification in Terms of Deep Convolutional Neural Networks with the Linkage of Visualizing Intermediate Layer Activations Detection. International Journal of Engineering and Modern Technology E-ISSN 2504-8848 P-ISSN 2695-2149 Vol 6 No 2 2020 www.iiardpub.org
41. Smith, J., & Johnson, E. (2025). A Hybrid Intelligence Framework for Real-Time Anomaly Detection in Smart Grid Transactions. Global Knowledge Academy, 6(3), 51-70.
42. Dalla, L. O. F. B. (2020). Convolutional Neural Network Baseline Model Building for Person Re-Identification. International Journal of Engineering and Modern Technology E-ISSN 2504-8848 P-ISSN 2695-2149 Vol. 6 No. 3 2020 www.iiardpub.org
43. Bhavikatta, N. B., & Goluguri, N. V. R. (2026). Multi dataset LSTM analysis for accurate and sustainable supply chain forecasting. Discover Sustainability.
44. Dalla, L. O. F. B. (2020). The Influence of hospital management framework by the usage of Electronic healthcare record to avoid risk management (Department of Communicable Diseases at Misurata Teaching Hospital: Case study).
45. Essien, I. A., Nwokocha, G. C., Erigha, E. D., Obuse, E., & Akindemowo, A. O. (2025). Hybrid AI Models for Real-Time Decision-Making in Dynamic Business Environments: A Comparative Study of XGBoost, LSTM, and Reinforcement Learning. International Journal of Scientific Research in Humanities and Social Sciences, 2(4), 156-174.
46. Dalla, L. O. F. B. (2020). Dorsal Hand Vein (DHV) Verification in Terms of Deep Convolutional Neural Networks with the Linkage of Visualizing Intermediate Layer Activations Detection..
47. Degirmenci, A., & Karal, O. (2022). Efficient density and cluster based incremental outlier detection in data streams. Information Sciences, 607, 901-920.
48. Dalla, L. O. F. B. (2020). Modeling by using Generic Modeling Environment (GME) Domain specific modeling language (DSL) for agile software development (ASD) types.
49. Mohanan, P. V. (Ed.). (2025). Artificial intelligence and biological sciences. CRC Press, Taylor & Francis Group.
50. Dalla, L. O. F. B. (2020). Convolutional Neural Network Baseline Model Building for Person Re-Identification..
51. Ersoy, E., & Karal, Ö. (2012). Yapay sinir ağları ve insan beyni. İnsan ve Toplum Bilimleri Araştırmaları Dergisi, 1(2), 188-205.
52. Dalla, L. O. B., Medeni, T. D., & Medeni, I. T. (2024). Evaluating the Impact of Artificial Intelligence-Driven Prompts on the Efficacy of Academic Writing in Scientific Research. Afro-Asian Journal of Scientific Research (AAJSR), 48-60.
53. Karal, Ö. (2024). Comparative performance analysis of epsilon-insensitive and pruningbased algorithms for sparse least squares support vector regression. Sigma Journal of Engineering and Natural Sciences, 42(2), 578-589.
54. Karal, Ö. (2024). Comparative performance analysis of epsilon-insensitive and pruningbased algorithms for sparse least squares support vector regression. Sigma Journal of Engineering and Natural Sciences, 42(2), 578-589.
55. Dalla, L. B., Karal, Ö., Mhamed, E. S., & Alsharif, A. (2026). An IoT-enabled, THD-based fault detection and predictive maintenance framework for solar PV systems in harsh climates: integrating DFT and machine learning for enhanced performance and resilience. Wadi Alshatti University Journal of Pure and Applied Sciences, 41-55.
56. Ben Dalla, L, O, F. Medeni, T, Medeni, I.(2024). Evaluating the Impact of Artificial Intelligence-Driven Prompts on the Efficacy of Academic Writing in Scientific Research
57. Ben Dalla, L, O, F. (2021).Literature review (LR) on the powerful of Research methodology processes life cycle. In 2021 Conference (TPRMPLCC) (pp. 1-10). IEEE. https://doi.org/10.16543/TPRMPLCC 50717.2020.92876580
58. Ben Dalla, L, O, F. (2021). Literature review (LR) on the dominant of Research methodology. Conference (LRDRMC) (pp. 1-14). IEEE. https://doi.org/10.6754/LRDRMC56412.2020.45987623
59. Rong, C. (2024). Operation and Management Optimization on Data-Driven Intelligent Parking Reservation Platform (Doctoral dissertation, ISCTE-Instituto Universitario de Lisboa (Portugal)).
60. Ben Dalla, L, O, F. (2021). The enhancement of English level of EFL learners by using English idioms while practices their English (Literature review). IEEE.EFLLEILR50303.2021.6592929
61. Soisoonthorn, T., & Unger, H. (2025). A Brain-Inspired Approach to Natural Language Processing. Springer Nature.
62. Dalla, L. O. B., Medeni, T. D., & Medeni, İ. T. (2024). Evaluating the Impact of Artificial Intelligence-Driven Prompts on the Efficacy of Academic Writing in Scientific Research. The journal of Afro-Asian Scientific Research (AAJSR), 48-60.
63. Ben Dalla, L,O, F, M.eljali , E, Agila, A,A,A, (2020). The evaluation of the daily profits of the group of cosmetics Sephora branches by using distributed systems the K-means algorithm and WEKA visualization. (KMAWV) (pp. 1-15). IEEE.https://doi.org/10. 32879/KMAWV50717.2020.65432879
64. Muttaqi, M., Degirmenci, A., & Karal, O. (2022, September). US accent recognition using machine learning methods. In 2022 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 1-6). IEEE.https://doi.org/10.1109/ASYU56188.2022.9925265
65. Ben Dalla. (2020). LANGUAGE PLANNING. Researchgate.com
66. Degirmenci, A., & Karal, O. (2022). Efficient density and cluster based incremental outlier detection in data streams. Information Sciences, 607, 901-920.
67. Karal, O. (2017). Maximum likelihood optimal and robust support vector regression with lncosh loss function. Neural networks, 94, 1-12.
68. Karal, Ö. (2020). Performance comparison of different kernel functions in SVM for different k value in k-fold cross-validation. In 2020 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 1-5). IEEE.
69. Ersoy, E., & Karal, Ö. (2012). Yapay sinir ağları ve insan beyni. İnsan ve Toplum Bilimleri Araştırmaları Dergisi, 1(2), 188-205.
70. Degirmenci, A., & Karal, O. (2021). Robust incremental outlier detection approach based on a new metric in data streams. IEEE Access, 9, 160347-160360.
71. KARAL, Ö. (2018). Destek vektör regresyon ile EKG verilerinin sıkıştırılması. Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 2018(2018).
72. Apaydın, M., Yumuş, M., Değirmenci, A., & Karal, Ö. (2022). Evaluation of air temperature with machine learning regression methods using Seoul City meteorological data. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 28(5), 737-747.
73. Degirmenci, A., & Karal, O. (2018). Evaluation of kernel effects on svm classification in the success of wart treatment methods. Am. J. Eng. Res, 7, 238-244.
74. Karim, A. M., Karal, Ö., & Çelebi, F. V. (2018). A new automatic epilepsy serious detection method by using deep learning based on discrete wavelet transform. In Proceedings of the 3rd International Conference on Engineering Technology and Applied Sciences (ICETAS) (Vol. 4, pp. 15-18).
