Ranking models are the machine learning-based algorithms that determine the optimal sort for a set of products.
Ranking models rely on a set of model features, or a collection of product attributes and metrics, to determine which products are most likely to be purchased. In addition to the default set of 40+ model features derived from your Google Analytics data, you can create custom model features using data imported from third-party sources. For more information on creating custom model features, view our support article here.
Convert's default ranking models cannot be modified. In order to add custom model features to a ranking model, you'll need to create a new ranking model first.
Table of Contents
Creating a Ranking Model
Ranking models are created at the site level, and cannot be shared between sites.
- Navigate to your Accounts list.
- Click on the Sites button for your account.
- Click on the Modeling button for the site.
- Click Add Ranking Model.
- Enter a unique and identifiable Name.
We recommend including the type of model you're creating for clarity. For example, if you're going to build a model that optimizes purchases, consider naming it something like "Purchases - [Descriptor]".
- Use the dropdown to select the Parent Model.
The parent model will determine a number of settings that cannot currently be configured, such as the goal of the model. Additionally, many configurable settings can be set to inherit from the parent, and will update whenever changed in the parent.
- Add any desired custom Model Features to the model, and use the dropdown to select their Local Configuration.
See the section below for more information on managing model features.
- Click Save.
Managing Model Features
Although you cannot currently manage the default model features derived from your Google Analytics data in a custom ranking model, you can add and enable custom model features that you've created from third-party data sources.
Adding a Custom Model Feature
- Navigate to an existing ranking model, or create a new one.
- In the Model Features section, use the dropdown in the Name column to select a model feature. This will add it to the ranking model.
If there are no empty rows available, click Add More Features at the bottom of the model features list.
- Once a feature has been added to the model, it can be enabled, disabled, or removed. Read on for more information.
Removing a Custom Model Feature
If you want to remove a model feature from the list, simply click the X button at the end of the row.
Once a feature has been removed, you'll need to add it again before it can be used by the ranking model.
Once you've added a feature to your ranking model, you'll need to configure whether or not the model should use it to generate its rankings. This is where the Local Configuration comes in.
Features can have one of three local configurations: Enabled, Disabled, or Inherited.
- Enabled features will be considered by the ranking model when generating its rankings.
- Disabled features will not be considered by the ranking model when generating its rankings.
- Inherited applies only to custom features that have been inherited from the parent model. When set to Inherited, the feature will follow whatever configuration is set on the parent model.
You can always tell what configuration is currently set on an inherited feature at the parent level by looking to the Effective Value column.
By default, all newly added features will have a Local Configuration set to Enabled.
Inherited Model Features
Any custom features inherited from the parent model will appear at the top of the Model Features list. These features cannot be removed, and can be identified because their Name dropdown will be inactive.
To override the configuration of an inherited feature on the current model, use the Local Configuration field. Once you've set a local configuration on an inherited feature, any changes made to the feature's configuration at the parent level will not impact the child model. If you want an inherited feature to resume inheriting its configuration from the parent model, simply set the local configuration to Inherited.
For clarity, the Effective Value column will always display the feature configuration to be used by the current model.
Using a Custom Ranking Model
Once you've created a custom ranking model, it will not be ready for immediate use.
First, a ranking model must train, which is where our machine learning technology processes all the data available to it, identifying and weighing key features, before ultimately establishing the algorithm it will use to rank products. Model training can take up to 24 hours from the time a new model has been created.
Once the custom ranking model is trained, it can be used to generate rankings just as any default model would be. You can view its rankings via the Product Lists or Product Referrers reports, or set it as the update source for a Product Positioning Group.
When experimenting with custom ranking models, we highly recommend running A/B tests to validate the effectiveness of new settings.