The Anomaly Detection and Prediction features are AT Internet’s two new timeseries functionalities seamlessly integrated within Explorer.
Currently, the Anomaly detection & Prediction functionalities are located within the “Data Science” option in the graph selection of the Overall Traffic > Audience Analysis.
Anomaly detection: Anomalies are detected when our statistical model identifies suspicious fluctuations for a given metric within the context of the analysis.
Note: As anomalies depend on the context, anomalies can change if you modify the analysis settings (for e.g. the timeframe).
Example: A large decrease in visits on a Saturday may seem to be suspicious within the context of a week however prove to be a perfectly ordinary fluctuation as the scale of a year (decreases in traffic can be observed at the end of each week).
Anomalies are illustrated on the graph with round symbols overlaid on the timeseries.
Positive anomalies will be shown in green:
Negative anomalies will show up in red:
Prediction: the prediction functionality will provide you with the expected future values for a given metric based on your historical data.
In daily granularity we forecast the following 7 days after the last day of the analysis.
In hourly granularity we forecast the following 24 hours after the last hour of the analysis.