Machine Learning

This document gives an overview of the characteristics and machine learning features.

Machine learning features of the commercetools platform provide automated predictions by autonomously learning from data. In general, these features make use of artificial intelligence to reduce the amount of manual work that is required to manage projects. For example, machine learning can be used to automatically predict which of potentially thousands of available categories fit best to a given product.

Since our machine learning features are in an early stage of development, your feedback can have a large impact. If there is anything you would like to tell us (positive experiences, criticism or requests for new features), please contact us via the platform support.

Currently, the following machine learning features are available:

Differences to other Endpoints

Compared to other endpoints of the commercetools platform, machine learning features have some characteristic differences:

  • The results are based on probabilities and have a margin of error, which is indicated by confidence scores in the responses (0.0 is low, 1.0 is high).
  • The response times are typically longer since the underlying computations can be complex.
  • The hosts are different and located at ml-eu.europe-west1.gcp.commercetools.com for projects in Europe and ml-us.europe-west1.gcp.commercetools.com for projects in the United States.

Confidence Filtering

Queries for a collection of predictions can optionally provide confidence bounds on the returned predictions. This allows users to specify that the endpoint should only return those predictions about which we are more confident than confidenceMin and less confident than confidenceMax.