The Anomaly Detection block will determine the data which do not conform to an expected pattern or to other items in a dataset. Typically the anomalous items will translate to some kind of problem such as bank fraud, a structural defect, medical problems, etc. Anomalies are also referred to as outliers, novelties, noise, deviations and exceptions.
Interpreting the results
The "Outlier Score" field will provide values between 0 and 1, the lower the value the less likely the record is to be an outlier. For example, in the below image the points with higher "Outlier Score" are clearly somewhat distinct from the main collection of points and have been detected successfully.