<![CDATA[In this rapidly growing digital era, the phenomenon of e-commerce has become a major highlight, the rapid growth of e-commerce has attracted more and more users. However, cases of sophisticated and dynamic fraud are increasing as the volume of transactions increases. This phenomenon not only poses a risk of financial loss for buyers and sellers but also threatens the trust that is so important in the e-commerce industry. To solve this problem, the author uses a random Forest AI-based Machine Learning approach in analyzing and finding fraud patterns to deal with fraud on e-commerce sites. The Random Forest model was chosen because of its excellent ability to handle complex e-commerce transaction data, including the ability to find non-linear patterns, its resistance to overfitting, and its scalability on large datasets. This model is expected to identify suspicious fraud patterns in e-commerce transactions. The method will involve data processing, feature selection, and model training using a dataset that includes ecommerce transactions. The results of this research are expected to contribute to a better understanding of fraud on e-commerce sites in the face of future fraud. Effective fraud detection is also expected to reduce the losses caused by fraud on e-commerce sites and protect users from the risk of fraud.]]>
Copyrights © 2024
