A Comparative Approach to Predictive Analytics with Machine Learning for Fraud Detection of Realtime Financial Data
Aakriti Singla, Hitesh Jangir
Abstract
With digital strategies coping up with banks and financial institutions, enormous data passed to these sectors, business transactions are becoming more prone to frauds and threats resulting in data leakage and personal details exposed to fraudsters leading to huge loss to organizations as well as to customers. This makes organizations adapt to high-level security and data handling technology solutions like machine learning, deep learning and predictive analytics which are efficient enough to deal with highly sensitive data, predict frauds and unwanted behavioural patterns in this data. This paper reviews the different advance technologies commonly used to deal with this type of data forms a comparison among them and suggests the most efficient and informative method to use in this sector. Through the end of the review, feature engineering and its selection of parameters for achieving better performance are discussed.