Anomaly Detection¶

The Anomaly Detection extension as part of the predict offering offers an out-of-the-box model building and detect the variations in your time series data values, using advanced artificial intelligence and machine learning technologies.

Anomaly Detection uses time series data from asset as dataset and performs easy configuration for model building and detection of anomalies.

The Anomaly Detection report visualizes the anomaly spots, indicators, which could be further utilized for your targeted use cases like comparing with threshold value, reviewing historic records.

User Interface¶

The following image shows the Anomaly Detection screen:

① Displays the Dataset information
② Displays the variable for which anomaly needs to be created
③ Data visualization area
④ Displays the configuration parameters

Building the Anomaly Detection model¶

To build the anomaly detection model, proceed with the following steps:

1. From the "Analyze" tab, click "Predict 2.0".
2. Select "Use Case", and click "Anomaly Detections".
3. In the "Training Dataset" section, select the "From Data" and "To Date" as the time period required for the training dataset for the model building.
4. Select the "Predicator Variables" and the "Timeseries Type".
5. Configure the "Perspective" and "Sensitivity" settings:
   • Residual Sensitivity: Detects the residuals with significantly higher magnitude than those observed on the in-sample period as anomalous.
     
   • Residual Change: Detects the most extreme changes compared to the anomalous behavior model can see on the in-sample period.
     
   • Fluctuation: Anomalous behavior model detects anomalies if different fluctuations are observed than those which were present during the in-sample period.
     
   • Fluctuation Change: The fluctuation change perspective focuses on the fluctuation of the residuals output similarly to the fluctuation perspective. However, the difference is that the fluctuation change perspective seeks only for the change in the fluctuation.
     
   • Imbalance Sensitivity: The imbalance perspective helps to detect anomalies accompanied by deviation of the residuals output from zero for a longer period of time.
     
   • Imbalance Change: Anomalous behavior model with an imbalance change perspective is suited for detecting anomalies that occur when a change of imbalance in the residuals output is observed.
     
6. Configure the "Data Imputation" setting by selecting the type from the drop-down.
   
7. For "Seasonality", click "On" or "Off" to enable or disable the seasonality.
   
8. Select "Polynomial" or "Fourier" to configure the type of "Feature".
9. Click "Build a model".
   

Schedule the Anomaly model for production¶

It is possible to schedule the production of the anomaly model which can be executed and evaluated on the regular intervals as per the preferred time range.

To schedule the production run of the anomaly model, proceed with the following steps:

1. Open "Predict 2.0" in the "Analyze" tab.
   
2. Select the "Use Case", and click "Anomaly Detections".
   
3. Select the preferred model from the list of available models.
   
4. Click Schedule for production.
   
5. Select the preferred frequency for executing the models.
   The anomaly models can be executed as per the below intervals:
   • Minutes
     
   • Hourly
     
   • Daily
     
   • Weekly
     
6. Select the date in the "Schedule Start Date" and "Schedule End Date".
   
7. Click "Deploy".

Anomaly Detection Results¶

Once the anomaly detection is scheduled for production, the anomalies are generated as per the schedule. The generated anomalies can be used to analyze the data for the selected variables of the asset. To view the anomaly detection, click "Production Detections" and select the preferred anomaly detections from the "Detail result for anomaly execution" drop-down.

Detecting the Anomalies¶

Once the model for anomaly detection is built, configure the "Testing Dataset" setting, the time period to execute the anomaly detection. Click "Detect" to start detecting the anomaly spots for the selected dataset.

Once the Anomaly detection is completed, the anomaly spots are displayed as shown below:

① Displays the selected variables and Anomalies
② Displays the anomaly indicators as per the perspectives
③ Displays the top predictors
④ Displays the Anomaly detection configuration details

Delete Anomaly Detections¶

To delete the generated anomaly detections, select the anomaly delections from the list, click and select "Delete".