# Navigating the ML deployment interface When you open your ML deployment, you can perform management and monitoring activities, and use it to create predictions on datasets. Open an ML deployment from the catalog. There are navigation options for the following: * [Deployment overview](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/ml-model-management.htm#Overview) * [Deployable models](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/ml-model-management.htm#Deployable) * [Batch predictions](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/ml-model-management.htm#Batch) * [Real-time predictions](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/ml-model-management.htm#RealTime) * [Operations monitoring](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/ml-model-management.htm#Operations) * [Data drift monitoring](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/ml-model-management.htm#Drift) ## Deployment overview The Deployment overview shows the features used in the model training and details for the deployment. Overview of the ML deployment Overview of the ML deployment Overview of the ML deployment ![Model overview pane.](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Resources/Images/ui-automl-manage-model_depl-overview.png) If the default model in the deployment is inactive, you are notified in a banner at the top of the screen. If you have the correct permissions, you can activate the model by clicking Activate model. For more information, see: * [Approving deployed models](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/approve-models.htm) * [Working with model approval as an administrator](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/Admin/mc-approve-models-admin.htm) ## Deployable models The Deployable models pane is where you can manage model aliases and configure which models are used for predictions. For more information, see [Using multiple models in your ML deployment](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/ml-deployment-available-models.htm). Deployable models pane in Qlik Predict Deployable models pane in Qlik Predict Deployable modelsDeployable models pane in Qlik PredictQlik Predict !['Deployable models' pane in \[\[\[Undefined variable CommonComponents.AutoML\]\]\] ML deployment interface](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Resources/Images/ui-automl_available-models.png) ## Batch predictions In Batch predictions, you can manage and run batch predictions using the ML deployment. Click Create prediction to create a prediction configuration, from which you run batch predictions. You can have several prediction configurations for an ML deployment. You can use the Actions menu the Three-dot menu icon in the table to: * View and edit details for prediction configurations * Run predictions from existing configurations * Edit and delete configurations * Create, edit, and delete prediction schedules for an existing configuration Batch predictions with an overview and Actions menu expanded Batch predictions with an overview and Actions menu expanded Batch predictionsBatch predictions with an overview and ActionsActions menu expanded ![Dataset predictions pane.](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Resources/Images/ui-automl-manage-model_batch-predictions.png) If you select Edit prediction configuration, the Prediction configuration pane is opened. You can compare the model and apply dataset schema side-by-side as you edit the prediction. If your deployment contains a time series model, you can also view important details about your defined time series problem, such as the forecast window, time step, and apply window. Batch predictions with side pane for prediction configuration Batch predictions with side pane for prediction configuration Batch predictionsBatch predictions with side pane for prediction configuration ![Prediction configuration menu and dataset schemas when creating predictions.](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Resources/Images/ui_ml-tutorial_batch-prediction.png) ## Real-time predictions The Real-time predictions pane gives you access to the real-time prediction endpoint in the Machine Learning API. If the default model in the ML deployment is activated for making predictions, this pane is visible. For information about creating real-time predictions, see [Creating real-time predictions](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/creating-real-time-predictions.htm). Information note The real-time predictions API is deprecated and replaced by the real-time prediction endpoint in the [Machine Learning API](https://qlik.dev/apis/rest/ml/). The functionality itself is not being deprecated. For future real-time predictions, use the real-time prediction endpoint in the Machine Learning API. For help with migrating from the real-time predictions API to the Machine Learning API, refer to [the migration guide on the Qlik Cloud developer portal](https://qlik.dev/apis/rest/automl-deployments/#migrate-from-the-automl-real-time-predictions-api-to-the-machine-learning-api). Real-time predictions pane Real-time predictions pane Real-time predictions pane ![Real time predictions pane.](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Resources/Images/ui_ml_realtime-predictions.png) ## Operations monitoring In Operations monitoring, you can monitor usage information for the ML deployment. You can view details about how the ML deployment is being used, such as how many prediction events succeed or fail, and how prediction events are typically triggered. For more information, see [Monitoring deployed model operations](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/monitor-model-operations.htm). Operations monitoring pane in ML deployment Operations monitoring pane in ML deployment Operations monitoringOperations monitoring pane in ML deployment ![Embedded analysis showing operations analysis for an ML deployment](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Resources/Images/ui_ml-ops-monitoring.png) ## Data drift monitoring In Data drift monitoring, you can monitor data drift for the ML deployment. With data drift monitoring, you can assess changes in the distribution of features in the source model. When significant drift is observed, it is recommended that you retrain or re-configure your model to account for the latest data, which may indicate new patterns in data trends. For more information, see [Monitoring data drift in deployed models](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/AutoML/monitor-drift.htm). Data drift monitoring pane in ML deployment Data drift monitoring pane in ML deployment Data drift monitoringData drift monitoring pane in ML deployment ![Embedded analysis data drift analysis for an ML deployment](https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Resources/Images/ui_ml-data-drift-monitor.png)