BigData applied to the Financial System
APIs specialized in technologies such as deep learning and machine learning serve financial institutions for product definition and customer segmentation, effective risk management or fraud detection.
The three key questions in the use of machine learning for the definition of products and services and the necessary segmentation of customers is where they come from, where they are and where the bank users go. For this, the creation of a predictive model that is interpretable by the operations teams is mandatory, with the client at the center of the business logic and that motivates concrete actions. The idea is to define services that meet the needs and interests of customers, both in the study of consumer habits and channels where banking users show a greater commitment.
Some financial market companies have specialized in solving these problems. Brighterion is one of the fintech that today stand out for its automatic learning services for the prevention of bank fraud associated with credit cards, to give an example. The company's products combine up to 10 artificial intelligence technologies, with which the machine is able to learn, predict and make decisions in real time. It is a cognitive computing platform. Brighterion has four anti-fraud products:
● iPrevent: The platform is able to record and learn the behavioral and consumption habits of the holders of each of the cards issued by a bank. The objective: to establish red lines that detect possible anomalous behavior in the use of these cards.
● iDetect: Tool able to detect violations of personal or security data related to credit cards and irregular transactions.
● iPredict: Risk prevention tool for bank loans.
● iComply: Use of unsupervised learning processes to detect international money laundering behavior. The platform receives data from numerous sources, always in real time, analyzes the data and follows the flow of money between customers and organizations to avoid laundering.
