When I did it, I was more focusing on unsupervised learning (like multivariate outlier and anomaly detection) rather than on supervised learning (as there's maybe a lack of historical cases confirmed as fraud and the non-detected fraud cases from the past are polluting your "good" part of the sample).
Visual Analytics (VA) is a great tool for "consumption" of the output of your models, but for the models themselves you will need Visual Statistics (VS) and / or Visual Data Mining and Machine Learning (VDMML).
Visual Analytics can be used as a front-end for (a big part of) VS and VDMML but there are better front-ends for VS and VDMML.
Registration is open! SAS is returning to Vegas for an AI and analytics experience like no other! Whether you're an executive, manager, end user or SAS partner, SAS Innovate is designed for everyone on your team. Register for just $495 by 12/31/2023.
If you are interested in speaking, there is still time to submit a session idea. More details are posted on the website.