Forecasting Demand for Eco-Friendly Vehicles Using Machine Learning Technologies in the Era of Management 5.0

Serhii Kozlovskyi, Tetiana Kulinich, Marcin Duszyński, Taras Popovskyi, Tetiana Dluhopolska (), Artur Kornatka and Yurii Popovskyi
Additional contact information
Serhii Kozlovskyi: Department of Entrepreneurship, Corporate and Spatial Economics, Vasyl’ Stus Donetsk National University, 21600 Vinnytsia, Ukraine
Tetiana Kulinich: Department of Management of Organizations, Lviv Polytechnic National University, 79000 Lviv, Ukraine
Marcin Duszyński: School of Business, National-Louis University, 33300 Nowy Sącz, Poland
Taras Popovskyi: Department of Management and Behavioral Economics, Vasyl Stus Donetsk National University, 21600 Vinnytsia, Ukraine
Tetiana Dluhopolska: Bohdan Havrylyshyn Education and Research Institute of International Relations, West Ukrainian National University, 46020 Ternopil, Ukraine
Artur Kornatka: School of Business, National-Louis University, 33300 Nowy Sącz, Poland
Yurii Popovskyi: Department of Marketing and Business Analytics, Vasyl Stus Donetsk National University, 21600 Vinnytsia, Ukraine

Sustainability, 2025, vol. 17, issue 10, 1-27

Abstract: Management 5.0 represents a new paradigm in business strategy and leadership that integrates sustainability, advanced digital technologies, and human-centered decision-making. The article explores the application of machine learning technologies for forecasting demand for eco-friendly vehicles as a key tool for enhancing manufacturers’ competitiveness. This research supports key UN Sustainable Development Goals (SDGs), including SDG 7 (Clean Energy), SDG 9 (Innovation and Infrastructure), SDG 11 (Sustainable Cities), and SDG 12 (Responsible Consumption). Based on an analysis of the European market from 2019 to 2023 and forecasting through 2027, a comprehensive approach was developed using ARIMA, Prophet, and Random Forest models. Empirical findings indicate that implementing predictive analytics can reduce inventory costs by 18–25% and optimize working capital by 15–20%. Model performance varied by market type: Random Forest excelled in smaller markets, while Prophet delivered strong results in trend-stable environments. The results confirm that accurate demand forecasting, supported by machine learning technologies, creates significant competitive advantages in the era of management 5.0 through production process optimization and improved market positioning.

Keywords: demand forecasting; eco-friendly transport; machine learning; hybrid model; supply chain sustainability; Management 5.0 (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/10/4429/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/10/4429/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:10:p:4429-:d:1654866

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().