\n
Inputs<\/h2>\n\nThe Anomaly Detection process allows configuration of multiple inputs.<\/p>\n
\n- Minimum: 1 input<\/li>\n
- Maximum: 100 inputs<\/li>\n<\/ul>\n
The primary input is based on the selected Source context, while additional inputs can be configured to supplement the analysis.<\/p>\n
Inputs can be defined using attributes, calculations, tags, entity attributes, or fixed values.<\/p>\n
Each configured input provides data values that are evaluated by the anomaly detection process.<\/p>\n
Read more: Adding an Anomaly Detection Process<\/a><\/p>\n
\nMachine Learning Model<\/h2>\n
The Anomaly Detection process uses machine learning to analyse input data. A model can be selected in the Model Settings<\/strong> section in the Process Panel.<\/p>\n![\"\"](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2026\/06\/model-settings-1080x181.png\")
<\/a><\/p>\nAvailable Models<\/p>\n
The following model is supported for the Anomaly Detection process:<\/p>\n
\n- IFS.ai Unsupervised (Low)<\/li>\n<\/ul>\n
This model provides a basic level of anomaly detection.<\/p>\n
Note: Only one machine learning model is currently available in this process. Additional models and configuration options are expected to be introduced in future releases.<\/p>\n<\/div>\n
\nState Transition Rules<\/h2>\n
The Anomaly Detection process determines state transitions based on the evaluation of input data. Transition from one state to another is equally dependent on the current evaluation of data, and on the current state.\u00a0<\/p>\n
State transitions cause events to be raised, allowing for the escalation of actions via the Sentinel framework. Different actions can be defined for each state outcome.<\/p>\n
In the Anomaly Detection process, the state transitions are based on whether the evaluated data is identified as normal or anomalous.<\/p>\n
For example, the Default state can transition to the Anomalous state when unusual behaviour is detected, and can return to the Default state when the data is considered normal again.<\/p>\n
\nTest Outcomes<\/h2>\n
The following outcomes are possible when the Anomaly Detection process is executed:<\/p>\n
\n\n\nDefault State<\/strong><\/td>\nData is not in an erroneous state and does not exhibit unusual behaviour.<\/td>\n<\/tr>\n \nAnomalous State<\/strong><\/td>\nData is identified as anomalous based on the model evaluation.<\/td>\n<\/tr>\n \nSuppressed State<\/strong><\/td>\nThe monitor has been suppressed. For example, if the precondition has not been met.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\nAdding an Anomaly Detection Process<\/h2>\n
Every test uses a specific type of process to evaluate monitor item data. The Anomaly Detection Process is used for testing continuous data using machine learning.<\/p>\n
The Anomaly Detection process allows configuration of multiple inputs.<\/p>\n
- \n
- Minimum: 1 input<\/li>\n
- Maximum: 100 inputs<\/li>\n<\/ul>\n
The primary input is based on the selected Source context, while additional inputs can be configured to supplement the analysis.<\/p>\n
Inputs can be defined using attributes, calculations, tags, entity attributes, or fixed values.<\/p>\n
Each configured input provides data values that are evaluated by the anomaly detection process.<\/p>\n
Read more: Adding an Anomaly Detection Process<\/a><\/p>\n
\nMachine Learning Model<\/h2>\n
The Anomaly Detection process uses machine learning to analyse input data. A model can be selected in the Model Settings<\/strong> section in the Process Panel.<\/p>\n
<\/a><\/p>\nAvailable Models<\/p>\n
The following model is supported for the Anomaly Detection process:<\/p>\n
- \n
- IFS.ai Unsupervised (Low)<\/li>\n<\/ul>\n
This model provides a basic level of anomaly detection.<\/p>\n
Note: Only one machine learning model is currently available in this process. Additional models and configuration options are expected to be introduced in future releases.<\/p>\n<\/div>\n
\nState Transition Rules<\/h2>\n
The Anomaly Detection process determines state transitions based on the evaluation of input data. Transition from one state to another is equally dependent on the current evaluation of data, and on the current state.\u00a0<\/p>\n
State transitions cause events to be raised, allowing for the escalation of actions via the Sentinel framework. Different actions can be defined for each state outcome.<\/p>\n
In the Anomaly Detection process, the state transitions are based on whether the evaluated data is identified as normal or anomalous.<\/p>\n
For example, the Default state can transition to the Anomalous state when unusual behaviour is detected, and can return to the Default state when the data is considered normal again.<\/p>\n
\nTest Outcomes<\/h2>\n
The following outcomes are possible when the Anomaly Detection process is executed:<\/p>\n
\n\n
\n Default State<\/strong><\/td>\n Data is not in an erroneous state and does not exhibit unusual behaviour.<\/td>\n<\/tr>\n \n Anomalous State<\/strong><\/td>\n Data is identified as anomalous based on the model evaluation.<\/td>\n<\/tr>\n \n Suppressed State<\/strong><\/td>\n The monitor has been suppressed. For example, if the precondition has not been met.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n
\nAdding an Anomaly Detection Process<\/h2>\n
Every test uses a specific type of process to evaluate monitor item data. The Anomaly Detection Process is used for testing continuous data using machine learning.<\/p>\n
- IFS.ai Unsupervised (Low)<\/li>\n<\/ul>\n
![](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2023\/03\/word-image-58865-33.png\")
panel.<\/p>\n![\"\"](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2026\/06\/AD-Process-1-1080x698.png\")
<\/a><\/p>\n![](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2023\/03\/word-image-58865-35.png\")
button to select an attribute. You are limited to selecting an attribute of the test source monitor items. This attribute of each of the monitor items is a separate process input.<\/p>\n![](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2023\/03\/word-image-58865-36.png\")
button to open the Edit Calculation window.\u00a0<\/p>\n![](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2023\/03\/word-image-58865-37.png\")
button to select an entity. From here, select an attribute, or attribute value, for the selected entity.<\/p>\n![](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2023\/03\/word-image-58865-41.png\")
button to select a tag.<\/p>\n![](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2023\/03\/word-image-58865-38.png\")
button, at the top right of the panel.<\/p>\n![\"\"](\"https:\/\/oihelp.corporate.ifs.com\/help\/wp-content\/uploads\/2026\/06\/state-config-1080x238.png\")
<\/a><\/p>\n