|
|
Neural Networks
A neural network is a powerful data modeling tool capable of capturing and representing complex relationships between incoming and outgoing information.
The need for neural network technology emerged from the desire to develop an artificial system that could perform “intelligent” tasks similar to those performed by the human brain.
These models learn the data directly from the financial institution, which is why their performance can be maintained and improved through periodic training sessions as new fraud and general transaction cases are presented in the market. They adapt to the institution’s and country’s realities.
The client’s characteristics, their profile, and data from new transactions feed the models. An exit will indicate to a specific degree of certainty if the transaction varies from those that the client usually makes or if it is in line with historical fraud transactions.
|
|
