Credit card fraud is among the most prominent financial frauds in the ever-growing industry. Credit card firms must detect fraudulent transactions to ensure clients are not billed for products they did not purchase. With technological advancements, fraudulent transactions have increased, driven by the proliferation of online payment options. Machine learning algorithms play a pivotal role in detecting fraud by analyzing transaction behavior. This study presents a model achieving 99.92% accuracy using techniques like Random Forest Classifier, SVC, and SGD Classifier. The model employs dataset preprocessing and sampling techniques such as SMOTE and SMOTEENN. Our findings highlight effective fraud detection mechanisms and their relevance to the financial industry.