IBM Safer Payments
IBM Safer Payments is the industry’s first true cognitive fraud prevention solution to payment processing and protects some of the largest and most complex payment portfolios in the world. Users report that IBM Safer Payments significantly reduces fraud losses while keeping false alarms to a minimum. This new approach services all payment channels.
How IBM Safer Payments is different
First generation payment fraud prevention solutions use coded expert experience. This included velocity counters and expert rules to identify high risk. The value of this approach was in its simplicity. However, the ever-increasing number and complexity of fraud patterns have rendered this approach inefficient.
Second generation solutions generated fraud detection models from past data. Neural networks and advanced statistics used for this typically required collecting large amounts of data over a long period of time. This data is then sent to the vendor that creates a model off site. By the time the model is put into production, the fraud patterns it detects can be a few years old.
Second generation solutions date back from a time when fraud patterns only changed slowly, so this was not too significant a problem. In today’s world, however, new patterns of fraud attack are frequently introduced and the speed of change is only accelerating.
As a result, neural network vendors have thus added first-generation rules engines to their products, so that the customers can create workarounds to their aging models. This is because neural networks are black boxes; they only generated a score that cannot be explained by looking at the model. In addition, the neural network model cannot be explicitly modified. Experience shows that some users of neural network-based solutions have moved away from dependence on the model and only use the rules function to mitigate cost and erratic performance.