Could Convolutional Neural Networks Help Identify Risk?

by ID Analytics

At ID:A Labs we’re always looking for new and more efficient ways to look at behavior patterns that may help us identify risk. In this video ID:A Labs Principal Data Scientist, Sunhyoung Han discusses her research involving Convolutional Neural Networks (CNN). A machine-learning architecture inspired by human brain cells, Convolutional Neural Networks are especially good at finding patterns in situations where the information may be hidden by noise. In this video, Sunhyoung shares how CNN technology could be utilized to detect changes in population behavior to differentiate fraud and credit types.