ONLINE FRAUD DETECTION

Fraud detection is an industrial application of data mining, business rules implementation and machine learning. The proposed solution defines the build and deploy of a custom ruleset and a machine learning model for online transactions to detect fraudulent transactions.

The proposed solution can be easily deployed On-Premises or on Azure.

The solution is consisted by SQL Server ML Services taking advantage of the power of SQL Server (2016 or higher) and ScaleR (Microsoft ML Server package) by allowing R to run on the same server as the database.

This solution will preprocess data, create new features, train R models, and perform predictions in-database. The predicted value, which can be interpreted as a probability of fraud, can help OPAP to determine whether they wish to try to interrupt the transaction.

FRAUD PREVENTION - nsKnox

Cybercriminals today are increasingly targeting corporate payments in their effort to defraud organisations out of millions of dollars. And with the number of attacks as well as the scope of financial damages continually on the rise it si clear that existing controls and security measures are simply not robust enough. This leaves organisations extremely vulnerable to cyberfraud attacks, including by means of social engineering and insider fraud, among others.

Our partner nsKnox, the global leader in B2B payments security offers this technology-driven approach with PaymentKnox. Powered by unique account validation technology the solution eliminates the vulnerabilities of manual processes with an automated, reliable, and highly secure approach to preventing fraud against outgoing and incoming payments.