GDS MODELLICA Machine Learning

While many unknown innovations will emerge over the next ten years, we are already experiencing the effects of some that have important implications for risk management. Over the next decade, shifts in customer expectations and technology are expected to cause massive alterations in banking and give it an entirely different profile. The rapid emergence and adoption of
artificial intelligence (AI) techniques like machine and deep learning are a wakeup call that will transform the technology landscape and touch almost every industry.
The rapid adoption of a new breed of models is offering much deeper insights into data. Machine learning identifies complex, nonlinear patterns in large data sets and makes more accurate risk models possible.

Risk functions should start to experiment with analytics (e.g., machine learning) in some areas, such as credit decisions. These algorithms have already significantly improved credit decisions on multiple occasions for some banks. These models learn with every bit of new information they acquire, improving their predictive power over time.

Machine Learning Model

PMML Consumer

An Open Standard for Sharing Models:

MODELLICA PMML Consumer allow Risk people to use the Predictive Model Markup Language (PMML), an XML-based predictive model interchange format conceived by the National Center for Data Mining at the University of Illinois at Chicago.

The module provides a way for analytic applications to describe and exchange predictive models produced by data mining and machine learning algorithms with Decision Studio. It supports common models such as logistic regression and neural networks.