Citation

Rabbi, Riadul Islam and Tusher, Ekramul Haque and Hasan, Mahmudul and Islam, Md Rashedul (2025) Application of Machine Learning Techniques in the Analysis of Sustainable Energy Finance. International Series in Operations Research and Management Science, 367. pp. 227-249. ISSN 0884-8289

Text 3.pdf - Published Version Restricted to Repository staff only Download (221kB)

Abstract

Sustainable energy finance is a vital aspect that drives modern economic frameworks. In earlier times, both demand and supply in global economies have been thought to consider energy prices such as different fuels. So, these energy sectors need to be sustainable in the world with eco-friendly state-of-the-art technologies. The objective of this investigation is to forecast several fuels like crude oil, heating oil, natural gas, gasoline, and Brent crude for future market directions to hold down in the world. The study employs different machine learning algorithms like Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNNs), Neural Network (NN), and XGBoost that a precise predicting model can successfully change the trends of fuel prices using historical Yahoo finance dataset. The findings from empirical research show that RF, DT, and XGBoost have given the best performance rather than other models. So cutting-edge technologies can contribute to the finance energy sectors to fulfill the sustainable development goals (SDGs) purposes. Above all, the carrying out of the SDGs could potentially be used to improve financial performance forecasting by enabling firms to enhance the involvement of investors and examine their ecological, governance, and social initiatives.

Item Type:	Article
Uncontrolled Keywords:	Machine learning, SDGs
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	27 Aug 2025 03:06
Last Modified:	27 Aug 2025 03:06
URII:	http://shdl.mmu.edu.my/id/eprint/14417

Downloads

Edit (login required)