The online payment method leads to fraud that can happen using any payment app. That is why Online Payment Fraud Detection is very important. Online Payment Fraud Detection using Machine Learning in Python. Here we will try to solve this issue with the help of machine learning in Python. The process begins with AI data input and preprocessing, utilizing the SMOTE technique to mitigate data imbalance, ensuring effective training and more reliable predictions. Our AI model undergoes thorough evaluation on three real-world financial transaction datasets, outperforming existing algorithms by 10% to 18% across various performance metrics. Additionally, it maintains excellent computational efficiency.  Online payment fraud detection refers to the methods, technologies, and strategies used to identify and prevent fraudulent activities in electronic transactions. As more and more transactions take place over the internet, particularly in e-commerce, online banking, and other digital services, fraud detection has become a critical part of securing online payments and safeguarding both consumers and businesses. In this innovative world, around 1 billion online exchanges occurred each day which benefits us with its administrations as well as prompts fake exercises. Wholesale fraud, monetary misrepresentation, taken cards, deliberate non-installment, complementary plan abuse lead to enormous income misfortune to the organization. The proficiency of E- Commerce is debasing step by step because of online extortion. A statistical approach ought to be taken to conquer these fake exercises and in this paper, we will talk about online extortion recognition system utilizing Machine Learning algorithms.