The unauthorized use of credit card information for fraudulent financial benefits by fraudsters without the knowledge of an unsuspecting users has become rampant due to financial inclusivity of financial institutions in their bid to reach both semi-urban and rural settlers. This in turn – has continued to ripple across the society with huge financial losses and lowered user trust implications for all cardholders. Thus, banks cum financial institutions are today poised to implement fraud detection schemes. 5-algorithms with(out) application of the synthetic minority over-sampling technique (SMOTE) were trained to assess how well they performed namely: Random Forest (RF), K-Nearest-Neighbor (KNN), Naive Bayes (NB), Support Vector Machines (SVM), and Logistic Regression (LR). Tested via flask, and integrated via streamlit as application programming interface on to various platforms – our experimental proposed RF ensemble performed best with an accuracy of 0.9802 after applying SMOTE; while LR, KNN, NB, SVM and DT yielded an accuracy of 0.9219, 0.9435, 0.9508, 0.5 and 0.9008 respectively. Our proposed ensemble achieved F1-score of 0.9919; while LR, KNN, NB, SVM and DT yields 0.9805, 0.921, 0.9125, and 0.8145 respectively. Results implies that proposed ensemble can be used with SMOTE data balancing technique for enhanced prediction for card fraud detection. Keywords: Random Forest, SMOTE, credit card fraud detection, feature selection, imbalanced dataset Otorokpo, A., Okpor, M.D., Yoro, E.R., Brizimor, S., Ifiokor, A.M., Obasuyi, D., Odiakaose, C.C., Ojugo, A.A., Atuduhor, R., Akiakeme, E., Ako, R.E., & Geteloma, V.O. (2024): DaBO-BoostE: Enhanced Data Balancing via Oversampling Technique for a Boosting Ensemble in Card-Fraud Detection. Journal of Advances in Mathematical & Computational Science. Vol. 12, No. 1. Pp 45-66. Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V12N2P4