Vulnerabilities in banking systems have increasingly exposed both customers and banks to fraudulent activities, resulting in substantial financial and reputational damage. Annually, financial fraud accounts for significant losses within the banking sector. Early detection of such fraud is crucial as it facilitates the development of counter-strategies and aids in mitigating these losses. This paper proposes a machine learning-based approach to enhance the effectiveness of fraud detection. We introduce an artificial intelligence (AI)-based model designed to expedite check verification processes and reduce the impact of counterfeit activities. Our research involves a detailed analysis of various intelligent algorithms trained on a publicly available dataset, specifically aiming to uncover correlations between certain factors and fraudulent activities. To address the prevalent issue of class imbalance within the dataset, we employed resampling techniques to achieve a more balanced data representation, thereby enhancing the accuracy and reliability of our proposed algorithm.