Fraud analytics is the use of big data analysis techniques to prevent online financial fraud. It can help financial organizations predict future fraudulent behavior, and help them apply fast detection and mitigation of fraudulent activity in real-time. More people are using online banking or managing their finances online every year. In 2020, the worldwide lockdown due to COVID19 convinced even more customers to use online banking for at least a portion of their financial activities. Fraud analytics applies machine learning techniques to financial data. Machine learning is a subset of Artificial Intelligence (AI). Where AI is the computer implementation of a human-like thought or decision-making process, machine learning uses mathematical algorithmic techniques to extract complex relationships within the data being analyzed. Fraud analytics uses machine learning to examine all the pertinent data regarding a transaction and assigns a risk score to the transaction. Based on the risk score it makes a recommendation to allow the transaction, block the transaction, or ask for step-up authentication before allowing the transaction. And this can all be done in real-time with or without human intervention, providing the financial institution with enhanced fraud prevention without causing undue friction in the customer session. Every transaction, from login to logout, can be examined for potential fraud risk. Data science is part of the solution. Financial Institutions collect huge amounts of behavioral, device and transactional data. Analysis of this data by the fraud detection system and/or fraud investigations team can be used in the prevention and detection of financial fraud. But the analysis will only be as good as the data in the data set. With good data, there are a number of big data analysis techniques that a machine learning-based fraud analytics system can use to combat financial fraud. Predictive analytics looks at patterns to make predictions on future, heretofore unknown events to understand the potential or propensity for fraud. Pattern recognition and anomaly detection identifies events that don’t conform to expected patterns. Machine learning algorithms can learn from the data and make predictions on future events.