A Data-Driven Decision Support System for Identifying Green Entrepreneurship Opportunities in the Banking System
Keywords:
decision support system, green banking, green credit assessment, environmental entrepreneurship, data-drivenAbstract
Objective: The present study aimed to develop a data-driven decision support system for identifying, evaluating, and prioritizing green entrepreneurship opportunities in the banking system by simultaneously considering financial, environmental, and credit risk indicators.
Methods and Materials: This study was conducted using a quantitative and data-driven approach. The required data were collected from three commercial and development banks and included financial indicators, green credit records, repayment histories, and environmental indicators such as carbon dioxide emission reduction, energy efficiency improvement, waste management, and resource consumption. In the multi-criteria decision-making phase, AHP and TOPSIS methods were employed for weighting and ranking projects, while Random Forest and XGBoost algorithms were used to predict project success. Furthermore, a multi-objective mathematical optimization model based on the NSGA-II algorithm was designed and implemented in Python to simultaneously optimize profitability, environmental performance, and credit risk.
Findings: The results demonstrated that the proposed decision support system successfully identified projects with the best balance between profitability and environmental performance. Projects P3 and P1 achieved the highest rankings and also showed the greatest selection frequency within the Pareto front generated by the NSGA-II algorithm. Scenario analysis indicated that increasing the available budget simultaneously improved profitability and environmental indicators, whereas stricter environmental constraints slightly reduced profit while significantly enhancing environmental performance. Sensitivity analysis further confirmed the robustness of the proposed model against moderate variations in input parameters, with substantial changes occurring only under extreme conditions.
Conclusion: The findings suggest that integrating a data-driven decision support system with multi-objective mathematical optimization can provide a comprehensive and reliable framework for green credit evaluation and optimal resource allocation in the banking sector. The proposed framework enhances decision-making accuracy while maintaining a balance among profitability, risk reduction, and sustainable development objectives, thereby offering a practical foundation for the advancement of intelligent green banking and sustainable financial policies.
Downloads
References
Al-Khatib, A. W. (2022). Can Big Data Analytics Capabilities Promote a Competitive Advantage? Green Radical Innovation, Green Incremental Innovation and Data-Driven Culture in a Moderated Mediation Model. Business Process Management Journal, 28(4), 1025-1046. https://doi.org/10.1108/BPMJ-05-2022-0212
Bibri, S. E. (2023). Data-Driven Smart Eco-Cities of the Future: An Empirically Informed Integrated Model for Strategic Sustainable Urban Development. World Futures, 79(7-8), 703-746. https://doi.org/10.1080/02604027.2021.1969877
Bickley, S. J., Macintyre, A., & Torgler, B. (2025). Artificial Intelligence and Big Data in Sustainable Entrepreneurship. Journal of Economic Surveys, 39(1), 103-145. https://doi.org/10.1111/joes.12611
Canakoglu, E., Erzurumlu, S. S., & Erzurumlu, Y. O. (2018). How Data-Driven Entrepreneur Analyzes Imperfect Information for Business Opportunity Evaluation. Ieee Transactions on Engineering Management, 65(4), 604-617. https://doi.org/10.1109/TEM.2018.2826983
Grant, E. (2021). Big Data-Driven Innovation, Deep Learning-Assisted Smart Process Planning, and Product Decision-Making Information Systems in Sustainable Industry 4.0. Economics, Management, and Financial Markets, 16(1), 9-19. https://doi.org/10.22381/emfm16120211
Hamzat, L., Abiodun, D., & Joseph, A. (2023). Empowering Entrepreneurial Growth through Data-Driven Financial Literacy, Market Research, and Personalized Education Tool. World Journal of Advanced Research and Reviews, 19, 1692-1711. https://doi.org/10.30574/wjarr.2023.19.2.1568
Khan, W., Nisar, Q. A., Roomi, M. A., Nasir, S., Awan, U., & Rafiq, M. (2024). Green Human Resources Management, Green Innovation and Circular Economy Performance: The Role of Big Data Analytics and Data-Driven Culture. Journal of Environmental Planning and Management, 67(10), 2356-2381. https://doi.org/10.1080/09640568.2023.2189544
Lazaroiu, G., Androniceanu, A., Grecu, I., Grecu, G., & Negurita, O. (2022). Artificial Intelligence-Based Decision-Making Algorithms, Internet of Things Sensing Networks, and Sustainable Cyber-Physical Management Systems in Big Data-Driven Cognitive Manufacturing. Oeconomia Copernicana, 13(4), 1047-1080. https://doi.org/10.24136/oc.2022.030
Liu, Y., Fang, W., Feng, T., & Gao, N. (2022). Bolstering Green Supply Chain Integration via Big Data Analytics Capability: The Moderating Role of Data-Driven Decision Culture. Industrial Management & Data Systems, 122(11), 2558-2582. https://doi.org/10.1108/IMDS-11-2021-0696
Makhloufi, L. (2024). Predicting the Impact of Big Data Analytics Capability and Green Absorptive Capacity on Green Entrepreneurship Orientation and Eco-Innovation. Journal of Enterprising Communities: People and Places in the Global Economy, 18(4), 746-770. https://doi.org/10.1108/JEC-05-2023-0069
Rane, S. B., & Narvel, Y. A. M. (2022). Data-Driven Decision Making with Blockchain-IoT Integrated Architecture: A Project Resource Management Agility Perspective of Industry 4.0. International Journal of System Assurance Engineering and Management, 13(2), 1005-1023. https://doi.org/10.1007/s13198-021-01377-4
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2025 Khadijeh Rajani, Maryam Rahmaty, Mohammd Ali Nasimi , Azam Hajiaghajani (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
