Towards data and analytics driven B2B-banking for green finance: A cross-selling use case study

This paper examines the role of technological innovation in banking and its potential effects on economic cycles. Specifically, it utilizes a case study of a German bank (Bank A) in the business-to-business (B2B) banking, including green finance, to demonstrate how leveraging advancements in data analytics and machine learning can enhance efficiency, risk management, and profitability. However, scaling these innovations poses risks if not managed carefully. The paper concludes with policy recommendations for utilizing technology responsibly while promoting sustainable economic growth. The methodology involves collecting and analyzing the bank's CRM and transactional data. Machine learning algorithms including neural networks, random forests, and support vector machines are applied to predict cross-selling opportunities. The models are evaluated. Key findings show that business area, transaction volumes, and product diversity are significant factors influencing cross-selling success. Random forest was confirmed the most effective algorithm, achieving 96.6 % accuracy. The data quality assessment revealed strengths in accuracy, completeness, and consistency. Areas needing improvement included enhancing interpretability and understanding of business terminologies. This research contributes to updated literature on data analytics adoption in B2B banking for green finance. It provides a practical framework to assess readiness and demonstrates the feasibility of predictive analytics. For practitioners, it delivers actionable insights into optimizing cross-selling and provides a prototype for leveraging data analytics in B2B banking. Limitations of the study and areas for further research are discussed.