A Novel Financial Anti-fraud Method based on Machine Learning Algorithms

Abstract

Digital finance is booming, financial technology is maturing, and the development of information technology has had a massively positive impact on society. However, such progress also introduces a new type of risk: the underground network industry is experiencing explosive growth, and telecommunications network fraud has caused enormous financial losses. In the age of digital finance, although commercial banks have ushered in new possibilities and created momentum, they must also confront new obstacles and needs for digital transformation. In this context, online financial services have emerged as the new primary battleground. In this study, based on the RFM high-dimensional derived features and machine learning techniques, a high-dimensional transaction behavior portraits-based anti-fraud machine learning model is created. Using big data, stream computing, and other technologies, as well as systematic deployment, application strategy, and iterative model optimization, we developed a set of machine learning-based in-event risk control solutions. Confirmed to have an AUC of 0.972, this model provides key insight into fraud risk, identifies fraudulent transactions in milliseconds, and has value and relevance for enhancing the in-transaction risk management capabilities of online digital financial organizations.