Answer:
Supervised anomaly detection is a process in data mining that uses a historic dataset of dependent variables and labeled independent variables to detect outliers or anomalies in the data been mined.
Unsupervised anomaly detection method uses unsupervised algorithms of unlabeled clusters to label and predicts and rule-out outliers or anomalies.
Step-by-step explanation:
Anomaly detection is a method of identifying data or observations with high deviation or spread from other grouped data. Supervised and unsupervised machine learning algorithms are used to predict and detect abnormal datasets or outliers during data mining.
The supervised anomaly detection algorithm trains the model with a dataset, for the algorithm to derive a function it could use to predict outlier or anomalies. The unsupervised detection algorithm is able to cluster and label normal and abnormal data in the dataset, using this function to detect anomalies in future datasets.