Anomaly Detection Using (Extended) Isolation Forest

By Adam Valenta (H2O.ai): Most of the existing anomaly detection algorithms are based on an assumption that precise knowledge of the normal observation behavior leads to a good understanding of anomalies. In other words, the algorithms are optimized to find a normal observation, not the anomalies themselves. Come and together we get on the bottom of anomaly detection with the (Extended) Isolation Forest algorithm used for unsupervised anomaly detection and designed specifically to reveal anomalies in the datasets.

This event takes place on-line (link is in the sidebar) and off-line:
GLAMI, Corso 2a, Křižíkova 148/34, 186 00, Prague 8. Reception desk will have all the necessary information.

After the event we will publish a recording and post a link to it in the comments.