Intelligent Machine Learning Framework for Lean-Based SAP Production Planning and Inventory Optimization
Keywords:
Machine Learning, SAP Production Planning, Lean Manufacturing, Inventory OptimizationAbstract
Manufacturing organizations increasingly require production planning systems that can respond to demand variability while maintaining low inventory, high resource utilization, and stable production flows. Conventional SAP-based planning approaches provide structured transactional and planning capabilities, but their effectiveness depends strongly on the quality of forecasting, parameter configuration, and interpretation of complex operational data. This paper proposes an Intelligent Machine Learning Framework for Lean-Based SAP Production Planning and Inventory Optimization that integrates lean decision principles with machine learning, dimensionality reduction, low-rank representation, and adaptive production-planning logic. The proposed framework transforms heterogeneous SAP planning information into analytically useful features, identifies dominant operational patterns, predicts demand and inventory requirements, and generates lean-oriented planning recommendations. Principal component analysis provides a theoretical basis for reducing redundant operational variables while preserving relevant information (Abdi and Williams, 2010). The framework additionally considers low-rank structures and singular-vector behavior to improve the stability and efficiency of high-dimensional learning processes (Agterberg et al., 2022; Bao et al., 2021). The methodology is designed as a decision-support architecture rather than a replacement for SAP transactional functionality. A conceptual evaluation demonstrates how the framework can improve forecast responsiveness, reduce unnecessary inventory buffers, identify production bottlenecks, and support more synchronized material planning. The findings indicate that combining lean principles with machine learning can create a more adaptive production-planning environment, although model stability, data quality, parameter sensitivity, and integration complexity remain important limitations.
Downloads
References
1. H. Abdi and L. J. Williams, Principal component analysis, Wiley Interdiscip. Rev. Comput. Stat., 2(4):433– 459, 2010.
2. J. Agterberg, Z. Lubberts, and C. E. Priebe, Entrywise estimation of singular vectors of low-rank matrices with heteroskedasticity and dependence, IEEE Trans. Inf. Theory, 68(7):4618–4650, 2022.
3. X. Anhao, Z. Pengyuan, P. Jielin, and Y. Yonghong, SVD-based DNN pruning and retraining, Tsinghua. Sci. Technol., 56(7):772–776, 2016.
4. J. Baik, G. Ben Arous, and S. Péché, Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices, Ann. Probab., 33(5):1643–1697, 2005.
5. Z. Bao, X. Ding, and K. Wang, Singular vector and singular subspace distribution for the matrix denoising model, Ann. Statist., 49(1):370–392, 2021.
6. Z. Bao and D. Wang, Eigenvector distribution in the critical regime of BBP transition, Probab. Theory Related Fields, 182(1-2):399–479, 2022.
7. F. Benaych-Georges and R. R. Nadakuditi, The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices, Adv. Math., 227(1):494–521, 2011.
8. F. Benaych-Georges and R. R. Nadakuditi, The singular values and vectors of low rank perturbations of large rectangular random matrices, J. Multivariate Anal., 111:120–135, 2012.
9. L. Berlyand, P.-E. Jabin, and C. A. Safsten, Stability for the training of deep neural networks and other classifiers, Math. Models Methods Appl. Sci., 31(11):2345–2390, 2021.
10. 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
Issue
Section
License
Copyright (c) 2026 Aditya Wijaya, Putri Maharani (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published by The Parthenon Frontiers and its associated journals are distributed under the terms of the Creative Commons Attribution (CC BY 4.0) International License unless otherwise stated.
Authors retain full copyright of their published work. By submitting their manuscript, authors agree to grant The Parthenon Frontiers a non-exclusive license to publish, archive, and distribute the article worldwide. Authors are free to:
-
Share their article on personal websites, institutional repositories, or social media platforms.
-
Reuse their content in future works, presentations, or educational materials, provided proper citation of the original publication.
