Most Risk Authentication Systems in the current IT industry offers a fraud modeling capability. Based on the historical data, this modelling capability can be built and created (manually) in Risk Authentication system. By using the available transaction data and system data, the model generates a score that describes the extent to which the model suspects a transaction’s genuineness.
With the advent of Big Data analytics and Machine Learning, Risk Authentication's Risk Engine can utilize those capabilities to take a big step forward towards Artificial Intelligence (AI). As the Risk Engine collects historical user data over time, Big Data analytics could be built into the Risk Engine to mine the data and let the Risk Engine auto adjust its Risk Modelling and Scoring by leveraging Machine Learning capabilities. With these new capabilities, besides auto adjusting these Risk Rules, Risk Engine can also makes Predictive Analysis against a user's Risk profile during login or while performing a transaction (sensitive/ risky).
In a nutshell, Risk Engines can be made smart enough to tune itself in modelling its own Risk Rules and Risk Scoring over a period of time without any manual intervention.