Search…
Intro to ML
Our APIs have Machine Learning (ML) capabilities baked into them. If you’re using our Building Blocks, you’re collecting data in a way that is already plugged into our ML tool set. These docs will explain what you can do with our ML tools and how to do it.
We have a few main types of ML models, recommendation, similarity and complementary. Just contact us if you'd like to expand that list. All ML models described in these docs share a set of common features and parameters.
Once you’re plugged into our APIs, you have access to several out-of-the-box recommendation and similarity models that apply to the most common use cases in our Simple ML section
You will go through the following phases for all ML models:
    1.
    Create the model on the dashboard. We automatically train and deploy it.
      1.
      The model can be retrained manually on the dashboard later on when more data is collected.
      2.
      An automatic evaluation that shows the validity of the model is created while the model is trained. This indicates how predictive the results should be.
    2.
    Query the recommendations or predictions online.
In order for you to be able to train models, you have to have some data or transaction history, e.g. users, products, orders and/or payments on our platform.
If you have no or a small amount of data, you will see the INSUFFICENT_DATA training status.

Machine Learning Model object

Attributes
Type
Description
model_name
string
The name of the model.
model_type
string
The model type.
description
string
The model description.
features
array
An array of strings with features.
target
string
What is used to query with.
output_type
string
The result of the query.
versions
array
List of objects with model versions.

Version object

Attributes
Type
Description
training_status
string
A string with the training status. Possible values: STARTING, CREATED, TRAINING, PENDING, READY, RUNNABLE, FAILED, SUCCEEDED, INSUFFICIENT DATA, JOB CANCELLED. Default is CREATED.
job_id
string
The AWS job ID.
status_reason
string
The reason for the failure.
Examples: deleting ds version, deleting ds model.
human_id
string
A human readable ID.
Last modified 1yr ago