Welcome
User Guide
Model Monitoring
This feature is available for classification and regression problem types.
Input Drift
Use Input Drift to understand the data distribution between the new dataset and the old dataset that are used to train the model. If the data maintains an acceptable level of variation, no further training is required to reuse the model. However, for an unacceptable range of variation in data distribution, you must retrain the model with the new dataset.

Release Notes
Installation Guide
Developer Guide
MLAC User Guide
User Guide
- Introduction
  Marketing AION (Artificial Intelligence ON) is an AI life cycle management platform for applying machine learning to real-world problems. Marketing AION encompasses the complete pipeline from raw data ingestion to a deployable machine learning model with a less-code/no-code approach.
- Model Management
- Model Training
- Model Prediction
  Model prediction predicts the input data based on the pattern of training data.
- Trusted AI
  This feature is available for classification and regression problem types.
- Model Monitoring
  This feature is available for classification and regression problem types.
  - Accessing Model Monitoring
    To access Model Monitoring, complete the following steps:
  - Input Drift
    Use Input Drift to understand the data distribution between the new dataset and the old dataset that are used to train the model. If the data maintains an acceptable level of variation, no further training is required to reuse the model. However, for an unacceptable range of variation in data distribution, you must retrain the model with the new dataset.
  - Performance Drift
    Use Performance drift to compare data distribution between the output data results and the label of input data providing details about the model performance.
- Utility
  For Data Generator and BYOM (Bring Your Own Model), select the Utility tab.

Input Drift

Use Input Drift to understand the data distribution between the new dataset and the old dataset that are used to train the model. If the data maintains an acceptable level of variation, no further training is required to reuse the model. However, for an unacceptable range of variation in data distribution, you must retrain the model with the new dataset.

About this task

To monitor the training data distribution, complete the following steps:

Procedure

Click Input.
Enter the current data file path.
Click Submit.
The distribution details are shown.
Click New data distribution.
The graph is shown.

To add feedback about this topic, select the following checkbox:

By clicking this box, you acknowledge that you are NOT a U.S. Federal Government employee or agency, nor are you submitting information with respect to or on behalf of one. HCL provides software and services to U.S. Federal Government customers through its partners Four, Inc. Contact this team at https://hcltechsw.com/resources/us-government-contact. Do not include any personal data in this Comment box. Note: To report a problem or question about the product software, do not use this form. Instead, go to the HCL Software Support site. Personal data should not be shared in this comment box. See our Privacy Statement to understand how personal data is used.