Machine Learning-Driven Cost Forecasting in Automotive Production Engineering: Towards Sustainable and Intelligent Manufacturing
Dorota KLIMECKA-TATAR, Muhammad Taimur HAMZA
Abstract. Accurate forecasting of manufacturing costs remains a central challenge for the automotive sector, where volatile supply chains, dynamic energy prices, and sustainability pressures continuously reshape production systems. This paper proposes a machine-learning-based framework for cost prediction in automotive production engineering, integrating historical pricing data, supplier performance, and material indices. Several regression models were trained and compared, including Linear Regression, Decision Tree, Random Forest, Gradient Boosting, and XGBoost. The XGBoost algorithm achieved the best performance (MAE = 34.49, R² = 0.90), confirming its robustness and interpretability for complex industrial datasets. Furthermore, the study explores stochastic and hybrid modeling techniques, combining deterministic ML prediction with uncertainty quantification to improve reliability under variable market conditions. The proposed approach demonstrates the potential of machine learning to support sustainable and intelligent manufacturing, enhancing both economic efficiency and resource responsibility.
Keywords
Machine Learning, Cost Prediction, Production Engineering, Automotive Production, Sustainability, Industry 4.0
Published online 1/25/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Dorota KLIMECKA-TATAR, Muhammad Taimur HAMZA, Machine Learning-Driven Cost Forecasting in Automotive Production Engineering: Towards Sustainable and Intelligent Manufacturing, Materials Research Proceedings, Vol. 62, pp 237-244, 2026
DOI: https://doi.org/10.21741/9781644904015-31
The article was published as article 31 of the book Terotechnology XIV
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] D. Klimecka-Tatar, M. Obrecht, Eco-design and sustainability in automotive production systems, Prod. Eng. Arch. 26 (2020) 131–137. https://doi.org/10.30657/pea.2020.26.25
[2] H. Lasi, P. Fettke, H.-G. Kemper, T. Feld, M. Hoffmann, Industry 4.0, Bus. Inf. Syst. Eng. 6 (2014) 239–242. https://doi.org/10.1007/s12599-014-0334-4
[3] S. Kamble, A. Gunasekaran, S. Gawankar, Industry 4.0 and lean manufacturing practices for sustainable organisational performance in Indian manufacturing companies, Int. J. Prod. Res. 56 (2018) 2979–2998. https://doi.org/10.1080/00207543.2018.1444806
[4] B. Tjahjono, C. Esplugues, E. Ares, G. Pelaez, What does Industry 4.0 mean to Value Stream Mapping?, Procedia Manuf. 51 (2020) 149–156. https://doi.org/10.1016/j.promfg.2020.10.021
[5] T. Stock, G. Seliger, Opportunities of sustainable manufacturing in Industry 4.0, Procedia CIRP 40 (2016) 536–541. https://doi.org/10.1016/j.procir.2016.01.129
[6] J. Bokrantz, A. Skoogh, C. Berlin, J. Stahre, Smart Maintenance: an empirically grounded conceptualization, Int. J. Prod. Econ. 223 (2019) 107534. https://doi.org/10.1016/j.ijpe.2019.107534
[7] C. Hennebold, K. Klöpfer, P. Lettenbauer, M. Huber, Machine learning-based cost prediction for product development in mechanical engineering, Procedia CIRP 107 (2022) 264–269. https://doi.org/10.1016/j.procir.2022.04.044
[8] P. Afonso, V. Vyas, A. Antunes, S. Silva, B. Bret, A stochastic framework for product costing in advanced manufacturing, Mathematics 9 (2021) 2238. https://doi.org/10.3390/math9182238
[9] A.A. ForouzeshNejad, F. Arabikhan, S. Aheleroff, Optimizing Project Time and Cost Prediction Using a Hybrid XGBoost and Simulated Annealing Algorithm, Machines 12 (2024) 867. https://doi.org/10.3390/machines12120867
[10] Y. Li, C. Stasinakis, W.M. Yeo, A hybrid XGBoost–MLP model for credit risk assessment on digital supply chain finance, Forecasting 4 (2022) 184–207. https://doi.org/10.3390/forecast4010012
[11] R. Ulewicz, Outsourcing quality control in the automotive industry, MATEC Web of Conferences (2018), https://doi.org//matecconf/201818303001
[12] N. Wagner, M. Ingaldi, Two faces of automation: cobots and autonomous mobile robots in action, Prod. Eng. Arch. 31(3) (2025), 276-290, https://doi.org/10.30657/pea.2025.31.27
[13] M. El Marzougui, N. Messaoudi, W. Dachry, B. Bensassi. A Model for Decision-Making to Parameterizing Demand-Driven Material Requirement Planning Using Deep Reinforcement Learning. Prod. Eng. Arch., 30(3) (2024), 377–393. https://doi.org/10.30657/pea.2024.30.37
[14] H. L. Yarfi, N. Motaki, M., Derrhi, I. Lahlou. Towards a Decision-Making Framework for Successful ERP Project Implementation: A Qualitative Study. Prod. Eng. Arch., 31(1) (2025) , 91–105. https://doi.org/10.30657/pea.2025.31.9
[15] D. Cetindamar, R. Phaal, Technology Management in the Age of Digital Technologies, IEEE Trans. Eng. Manag. 70 (2023) 2507–2515. https://doi.org/10.1109/TEM.2021.3101196
[16] M. Abdel-Jaber, N. Makhoul, M. Abdel-Jaber, R. Beale, Cost prediction for product development using hybrid deep learning model: a meta-heuristic model, Multimed. Tools Appl. 84 (2025) 33307–33330. https://doi.org/10.1007/s11042-024-20437-y
[17] D.-J. Pang, Hybrid Machine Learning Model Performance in IT Project Cost and Duration Prediction, Adv. Sci. Technol. Eng. Syst. J. 8 (2023) 108–115. https://doi.org/10.25046/aj080212
[18] J. Pietraszek, A. Gadek-Moszczak and T. Toruński, Modeling of errors counting system for PCB soldered in the wave soldering technology, Advanced Materials Research 874 (2014) 139-143. https://doi.org/10.4028/www.scientific.net/AMR.874.139
[19] R. Dwornicka et al., Fuzzy Statistics-Aided Inference in Experimental Design, World Congress in Computational Mechanics and ECCOMAS Congress (2024). https://doi.org/10.23967/wccm.2024.131
[20] J. Pietraszek, Fuzzy regression compared to classical experimental design in the case of flywheel assembly, Lecture Notes in Computer Science 7267 LNAI (2012) 310-317. https://doi.org/10.1007/978-3-642-29347-4_36
[21] J. Pietraszek, The modified sequential-binary approach for fuzzy operations on correlated assessments, Lecture Notes in Computer Science 7894 LNAI (2013) 353-364. https://doi.org/10.1007/978-3-642-38658-9_32
[22] G. Filo, A Review of Fuzzy Logic Method Development in Hydraulic and Pneumatic Systems, Energies 16 (2023) art. 7584. https://doi.org/10.3390/en16227584
[23] A. Pacana, D. Siwiec, Method of Fuzzy Analysis of Qualitative-Environmental Threat in Improving Products and Processes (Fuzzy QE-FMEA), Materials 16 (2023) art. 1651. https://doi.org/10.3390/ma16041651
[24] M. Nowicka-Skowron, R. Ulewicz, Quality management in logistics processes in metal branch, METAL 2015 – 24th Int. Conf. Metall. Mater. (2015) 1707-1712.
[25] R. Ulewicz et al., Logistic controlling processes and quality issues in a cast iron foundry, Materials Research Proceedings 17 (2020) 65-71. https://doi.org/10.21741/9781644901038-10
[26] D. Siwiec et al., Improving the non-destructive test by initiating the quality management techniques on an example of the turbine nozzle outlet, Materials Research Proceedings 17 (2020) 16-22. https://doi.org/10.21741/9781644901038-3
[27] R. Ulewicz, Quality management system operation in the woodworking industry, The Path Forward for Wood Products: A Global Perspective – Proceedings of Scientific Papers (2016) 51-56.
[28] R. Ulewicz, Outsorcing quality control in the automotive industry, MATEC Web of Conf. 183 (2018). https://doi.org/10.1051/matecconf/201818303001
[29] R. Ulewicz, F. Novy and R. Dwornicka, Quality and work safety in metal foundry, METAL 2020 – 29th Int. Conf. Metall. Mater. (2020) 1287-1293. https://doi.org/10.37904/metal.2020.3649
[30] A. Pacana, K. Czerwinska and R. Dwornicka, Analysis of quality control efficiency in the automotive industry, Transportation Research Procedia 55 (2021) 691-698. https://doi.org/10.1016/j.trpro.2021.07.037
[31] N. Radek et al., The influence of plasma cutting parameters on the geometric structure of cut surfaces, Materials Research Proceedings 17 (2020) 132-137. https://doi.org/10.21741/9781644901038-20
[32] D. Nowakowski et al., Application of machine learning in the analysis of surface quality – the detection the surface layer damage of the vehicle body, METAL 2021 – 30th Int. Conf. Metall. Mater. (2021) 864-869. https://doi.org/10.37904/metal.2021.4210
[33] A. Dudek et al., Laser Surface Alloying of Sintered Stainless Steel, Materials 15 (2022) art. 6061. https://doi.org/10.3390/ma15176061
[34] W. Przybył et al., Microwave absorption properties of carbonyl iron-based paint coatings for military applications, Defence Technology 22 (2023) 1-9. https://doi.org/10.1016/j.dt.2022.06.013
[35] N. Radek et al., Operational properties of DLC coatings and their potential application, METAL 2022 – 31st Int. Conf. Metall. Mater., (2022) 531-536. https://doi.org/10.37904/metal.2022.4491
[36] N. Radek et al., The effect of laser treatment on operational properties of ESD coatings, METAL 2021 – 30th Int. Conf. Metall. Mater. (2021) 876-882. https://doi.org/10.37904/metal.2021.4212
[37] N. Radek et al., Technology and applications of ESD coatings before and after laser processing, METAL 2023 – 32nd Int. Conf. Metall. Mater. (2024) 500-505. https://doi.org/10.37904/metal.2023.4727
[38] A. Kalinowski et al., Laser surface texturing: characteristics and applications, System Safety: Human – Technical Facility – Environment 5 (2023) 240-248. https://doi.org/10.2478/czoto-2023-0026
[39] J. Pietraszek, A. Goroshko, The heuristic approach to the selection of experimental design, model and valid pre-processing transformation of DoE outcome, Advanced Materials Research 874 (2014) 145-149. https://doi.org/10.4028/www.scientific.net/AMR.874.145
[40] J. Pietraszek, N. Radek and A.V. Goroshko, Challenges for the DOE methodology related to the introduction of Industry 4.0, Production Engineering Archives 26 (2020) 190-194. https://doi.org/10.30657/pea.2020.26.33
[41] Ł.J. Orman et al., Comparative Analysis of Indoor Environmental Quality and Self-Reported Productivity in Intelligent and Traditional Buildings, Energies 16 (2023) art. 6663. https://doi.org/10.3390/en16186663
[42] J. Pietraszek, A. Gadek-Moszczak, The smooth bootstrap approach to the distribution of a shape in the ferritic stainless steel AISI 434L powders, Solid State Phenomena 197 (2013) 162-167. https://doi.org/10.4028/www.scientific.net/SSP.197.162
