An Enhanced Electronic Banking Transaction System Through Blockchain Technology Based Fintech Developments and Adaptive Modelling
DOI:
https://doi.org/10.69996/fmep.2026027Keywords:
Electronic Banking Transaction System, Synthetic Minority Oversampling Technique (SMOTE), Autoregressive Integrated Moving Average (ARIMA), Poof of Work (PoW), SHA-256 MethodAbstract
To explores mobile money's effects on Ghana's banking sector—accessibility, safety, and productivity—alongside millennial brand loyalty post-e-CRM, highlighting blockchain and machine learning for security. Improving e-banking and microchip cards is crucial for customer retention in Banking 5.0. to overcome this issue a new model Blockchain Technology based Fintech Developments and Adaptive Modelling (BTFDAM). Data analysis, blockchain, and fintech enhance secure electronic banking transactions. A dataset with 123,545 rows uses the SMOTE method to address fraud, including attributes like account info, transaction amount, device, merchant class, and timestamp. Statistical analysis identifies transaction features in semi-urban and rural areas. ARIMA predicts daily mobile-money volumes, utilizing recursive forecasting for volume and fraud based on Ljung-Box Q test results. Transaction security is ensured through processing, validation, blockchain production, proof of work, and consensus analysis. SHA-256 hashing protects against denial-of-service attacks. Transaction processing involves decryption, key generation, expiration, sender info, and tag management, all requiring valid ratings. Verified transactions are logged with identifiers, hashes, and timestamps for security. Irving Fisher's model assesses money demand through supply, velocity, price, goods availability, income, financial innovations, and inflation for secure fintech payments. The performance analysis is BTFDAM processing time, ROC Curve, confusion matrix, overall performance, comparative accuracy calculations.
References
1] Rudra Bhanusri and N. Ramana Reddy, “Fraud Detection in Banking Transactions Using Machine Learning,” IJARI, vol. 13, no. 3, pp. 27–36, 2025.
[2] R. S. Nugroho and Z. D. Billah, “Exploring the impact of mobile banking as an electronic customer relationship management tool on Indonesian millennials’ brand loyalty,” Procedia Computer Science, vol. 284, pp. 160–167, 2026.
[3] A. Alenizi, S. Mishra and A. Baihan, “Enhancing secure financial transactions through the synergy of blockchain and artificial intelligence,” Ain Shams Engineering Journal, vol. 15, no. 6, 2024.
[4] L. Kim, K. Wichianrat, and S. F. Yeo, “An integrative framework enhancing perceived e-banking service value: A moderating impact of e-banking experience,” Journal of Open Innovation: Technology, Market, and Complexity, vol. 10, no. 3, 2024.
[5] L. Kim, N. K. Rakangthong, C. Lak, and S. Aujirapongpan, “A competency mechanism for customer trust enhancement in digital banking services,” Journal of Open Innovation: Technology, Market, and Complexity, vol. 12, no. 2, 2026.
[6] A. Harkai, “Managing cyber-security risks associated with IoT devices for conducting financial transactions within the smart home ecosystem,” Procedia Computer Science, vol. 242, pp. 200–210, 2024.
[7] O. O. Oyadeyi, “Financial innovation and money demand in Nigeria: Exploring the impact of banking innovations, fintech developments and digital payment channels on the money demand,” Social Sciences & Humanities Open, vol. 12, 2025.
[8] P.Sai Sudiptha, Yanamaddi Ravindra, Yalaka Ganesh, Putta Rama Goud, and S.Vamshi Krushna, “Future of Loan Approvals with Explainable AI,” IJARI, vol. 13, no. 3, pp. 19–26, 2025.
[9] F. Liébana-Cabanillas, G. A. Abbasi, E. Higueras-Castillo, and R. Wagner, “Press to pay: The power of biometrics in financial transactions investigated by PLS-SEM, fsQCA, and NCA,” Technological Forecasting and Social Change, vol. 221, 2025.
[10] J. Domashova and O. Zabelina, “Detection of fraudulent transactions using SAS Viya machine learning algorithms,” Procedia Computer Science, vol. 190, pp. 204–209, 2021.
[11] S. Ullah, C. Y. Liew, and H. Nobanee, “Digital transactions and financial development: The moderating role of global integration across income levels,” International Review of Economics & Finance, vol. 98, 2025.
[12] R. A. Kasri, B. S. Indrastomo, N. D. Hendranastiti and M. B. Prasetyo, “Digital payment and banking stability in emerging economy with dual banking system,” Heliyon, vol. 8, no. 11, 2022.
[13] C.-H. Tsai, D.-K. Liou and H.-L. Lee, “Blockchain-supported online banking scheme,” Egyptian Informatics Journal, vol. 27, 2024.
[14] M. N. Khatun, M. N. I. Sarker, and S. Mitra, “Adoption of mobile banking to promote financial inclusion among rural farming community: Drivers and satisfaction level perspective,” Journal of Agriculture and Food Research, vol. 18, 2024.
[15] D. Namakhwa, B. H. M. Tchereni, W. Masanjala, C. D. Namakhwa, S. L. Kuchande and W. R. Mgomezulu, “Modelling and forecasting mobile money customer transaction volumes in rural and semi-urban Malawi: An autoregressive integrated moving average spatial decomposition,” Scientific African, vol. 26, 2024.
[16] B. S. Prashanth, M. Kumar, A. Hoque, N. Al Muraqab, I. A. Moonesar, U. C. Braendle and A. Rao, “Prediction of bank transaction fraud using TabNet—an adaptive deep learning architecture,” International Review of Economics and Finance, vol. 106, 2026.
[17] L. Shoja, S. Ghavidel Doostkouei, M. Mahmoodzadeh and M. Soufimajidpour, “Evaluating the environmental impact of internet and mobile banking transactions,” Sustainable Futures, vol. 11, 2026.
