Adaptive Machine Learning Approach for Lean SAP Production Planning and Real-Time Inventory Optimization
DOI
Keywords
Abstract
Manufacturing organizations increasingly require production planning systems that can respond to demand variability, inventory uncertainty, process disturbances, and continuously changing operational conditions. Conventional SAP production planning approaches provide structured transaction and planning capabilities, but their effectiveness can be constrained when planning decisions depend on static parameters, manually adjusted forecasts, or optimization procedures that do not adequately adapt to changing data patterns. This research proposes an adaptive machine learning approach for lean SAP production planning and real-time inventory optimization. The proposed framework integrates stochastic approximation, adaptive optimization, non-convex learning, and convergence-oriented machine learning principles with SAP-oriented production and inventory decision processes. The methodological foundation is derived exclusively from the supplied literature on stochastic approximation, gradient-based optimization, implicit regularization, proximal algorithms, heavy-ball methods, and convergence behavior. The framework conceptualizes SAP planning as an adaptive decision problem in which demand signals, inventory states, production constraints, and replenishment requirements continuously update model parameters. A hybrid optimization architecture is proposed to balance responsiveness, computational stability, inventory reduction, and production throughput. The analysis indicates that adaptive learning can strengthen lean planning by reducing dependence on fixed planning assumptions while maintaining controlled optimization behavior. The study further identifies the importance of convergence conditions, learning-rate management, stochastic variability, and model stability for operational deployment. The proposed framework provides a theoretically grounded foundation for integrating adaptive machine learning into SAP production planning and real-time inventory management while recognizing limitations associated with data quality, non-convex optimization, computational requirements, and operational constraints.
References
P.-A. Absil, R. Mahony, and B. Andrews, Convergence of the iterates of descent methods for analytic cost functions, SIAM J. Optim., 16(2):531–547, 2005.
S. Arora, N. Cohen, W. Hu, and Y. Luo, Implicit regularization in deep matrix factorization, Adv. Neural Inf. Process. Syst., Vol. 32, 2019.
H. Attouch and J. Bolte, On the convergence of the proximal algorithm for nonsmooth functions involving analytic features, Math. Program., 116:5–16, 2009.
J.-F. Aujol, C. Dossal, and A. Rondepierre, Convergence rates of the heavy-ball method under the Łojasiewicz property, Math. Program., 198(1):195–254, 2023.
F. Bach and E. Moulines, Non-asymptotic analysis of stochastic approximation algorithms for machine learning, Adv. Neural Inf. Process. Syst., 24:451–459, 2011.
F. Bach and E. Moulines, Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n), Adv. Neural Inf. Process. Syst, 26:773–781, 2013.
R. Bassily, M. Belkin, and S. Ma, On exponential convergence of SGD in non-convex over-parametrized learning, arXiv:1811.02564, 2018.
M. Benaı̈m, Dynamics of stochastic approximation algorithms, in: Séminaire de Probabilités XXXIII. Lecture Notes in Mathematics, Springer, Vol. 1709, 1999.
A. Benveniste, M. Métivier, and P. Priouret, Adaptive Algorithms and Stochastic Approximations, in: Applications of Mathematics, Springer-Verlag, Vol. 22, 1990.
D. P. Bertsekas and J. N. Tsitsiklis, Gradient convergence in gradient methods with errors, SIAM J. Optim., 10(3):627–642, 2000.
P. Cheridito, A. Jentzen, and F. Rossmannek, Non-convergence of stochastic gradient descent in the training of deep neural networks, J. Complexity, 64:101540, 2021.
R. Chill, A. Haraux, and M. A. Jendoubi, Applications of the Łojasiewicz-Simon gradient inequality to gradient-like evolution equations, Anal. Appl. (Singap.), 7(4):351–372, 2009.
L. Chizat, E. Oyallon, and F. Bach, On lazy training in differentiable programming, Adv. Neural Inf. Process. Syst., 32:2937–2947, 2019.
E. Chouzenoux, J.-B. Fest, and A. Repetti, A Kurdyka-Łojasiewicz property for stochastic optimization algorithms in a non-convex setting, arXiv:2302.06447, 2023.
M. Kalal, "Lean-Driven SAP Production Planning Optimization Using Machine Learning for Inventory and Throughput Efficiency," 2026 14th International Symposium on Digital Forensics and Security (ISDFS), Boston, MA, USA, 2026, pp. 1-6, doi: 10.1109/ISDFS69419.2026.11459029.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Amir Hossein Rahimi, Leila Farzan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their articles published in this journal. All articles are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly cited.