It is a building block that helps in determining the needs attributes that are used by the runtime application in recommending the best matching products.

A few examples of IPSP naming formats are:

  • Abc_123

  • ABC123

  • 12345

  • 123aBC

The targets are product category and solutions of an IPSP.. There can be only one product category in an ML profile whereas there can be multiple solutions.

The deployed models are used to makde product recommendations in the runtime app.

You can unpublish an ML profile only if there's another ML profile with the same IPSP is available to be published.

ML models use algorithms to learn from. You can get useful insights and predictions using an ML model.

Product categories have only one type of ML model. Solution targets can have two types of ML models. They are:

Configuration Determination: This type of ML model helps in determining the best composition and make of the recommended products.

Commerical Attribute Determination: This type of ML model helps in determining the commercial attributes such as, lead time, and price predictions of the recommended products.

The model can anticipate outcomes by changing its internal parameters in response to the input data during training.

If the model meets the requirements, it needs to be deployed so that it can make real-time predictions.

If the model's performance deteoriates, its predictions won't be accurate.

The three ML model statuses are:

  1. Generating Training File: This is the stage when the training file of the ML model is being generated.

  2. Training File Generated, Ready for Training: At this stage, the Train button is enabled, and you can start training the model.

  3. Trained: The ML model's training is completed.

These are the settings for displaying product results in the runtime application.