This screen serves as a centralized workspace for managing machine learning models throughout their lifecycle. It is designed to streamline the management of all machine learning models that have been trained, allowing users to monitor their progress, organize them effectively, and make deployment decisions.

The primary purpose of this interface is to facilitate the end-to-end workflow of machine learning model management. Users can track the status of their models, from training to deployment, ensuring transparency and efficiency in the development process. Once a model completes its training successfully, the user has the option to deploy it to an API for serving, enabling real-time inference and integration into production systems.

This feature is critical for organizations leveraging machine learning, as it bridges the gap between model development and operationalization. By deploying models to APIs, users can provide services such as anomaly detection, forecasting, or predictive analytics to other applications or stakeholders in a seamless and scalable manner.

The interface also ensures ease of navigation with hierarchical folder structures, intuitive status indicators, and actionable controls, empowering users to manage their machine learning models with minimal effort and maximum productivity.

Below table show the description of Models configurable items

Configurable Items	Description
Model Name	Displays the name of the machine learning model.
Model ID	Shows the unique identifier for each model.
Mode Type	Specifies the type of machine learning model (e.g., Anomaly Detection, Forecasting ...).
Dataset Name	Indicates the dataset used for training the model.
Created Date	Shows when the model was created
Training status	Indicates whether the training is in progress or completed.
Deployment status	Shows if the model is deployed and serving through an API.
Action	Allows users to deploy a model to an API for serving or stop an already running model API.