Anomalies are infrequent data points, statistically different from the others, such as fraudulent credit card transactions. They can be detected from labeled and unlabeled data, with machine learning models that predict the fraud as one class, with autoencoders that fail to reconstruct fraudulent transaction data, with distribution-based techniques - along with many other supervised and unsupervised approaches.
Join Maarit Widmann and Rosaria Silipo in this free webinar! Based on the example of a credit card fraud detection problem, we will go through a number of different anomaly detection techniques, their logic and prerequisites, and compare their performances in credit card fraud detection. We’ll have time to answer your questions, too!
You’ll receive a zoom link with your registration confirmation. Make sure you have a stable internet connection!
Absolutely - fire away!
Download the latest free, open source version of knime here: knime.com/download