Vidora
Along with many third-party integrations, Zephr offers an integration with Vidora – a machine learning pipeline platform that allows companies to build and use complex machine learning models. Zephr customers use Vidora in a variety of ways, including propensity scoring for users.
When used within Zephr rules and decisions, information such as propensity scores and percentiles allow you to provide more custom, data-driven journeys for your end-users, based upon the outcome that you think they will best respond to. This could include offering subscription discounts to users who seem less likely to subscribe, or offering additional content to loyal users.
Main Features
- Support for both percentile and score output from Vidora Pipelines
- Support for manual score banding
- Integrates with Zephr’s rule builder canvas for easy, graphical configuration
- Dynamically queries active pipelines in your Vidora environment
Configuring Vidora with Zephr
To begin your configuration, navigate to Settings > Plugins > Vidora Next within your Zephr Admin Console. If Vidora isn’t available within your Plugin list, email support@zephr.com.
Within the configuration page, you’ll need to enter your Vidora API Details. This includes an API Key, an API Secret, and – if you’re using JWT tokens with Zephr – a JWT Claim for the Vidora User ID. Here you can also set your timeout length, which dictates when Zephr will timeout on the call to Vidora if a score is not being returned in a timely fashion.
The latest version of the Vidora plugin also maintains functionality for users to provide their own score banding config, although it is expected that the new support for percentile values will reduce the need for custom bands.
Vidora API Details
You will need to fetch your Vidora API Key and API Secret from your Cortex account. To find these, please sign into your Cortex account, then navigate to APIs > Documentation.
Note: if you are unable to access the API section, or cannot see the credentials, please contact Vidora for assistance.
Once you have the API Key and Secret, add them to the relevant fields on the Vidora API Details page:
You’ll also need to add:
- The JWT claim for the Vidora User ID
- A timeout in milliseconds. This value is the maximum overhead you’re prepared to tolerate on page load times whilst the percentile and score data is retrieved from Vidora.
Vidora Manual Score Banding
Once you’ve added your API credentials, click into the Mapping tab to map your Vidora Score Banding to Zephr.
Vidora Score Banding allows you to set ‘bands’ for your Vidora Scores. Bands are helpful if you wish to group a series of Vidora scores as a user segment. The example below shows this. As you will see, the mapping provides three bands for scoring – a score between 0 and 0.25 bands users into the Low Propensity group, 0.25 – 0.75 is classified as Medium Propensity, and 0.75 – 1 is classified as High Propensity. This mapping is set as a JSON object, specifying the Vidora Model at the beginning of the object.
{
"abcdefgh12345678": [
{
"from": 0,
"to": 0.25
"band": "Low Propensity"
},
{
"from": 0.25,
"to": 0.75,
"band": "Medium Propensity"
},
{
"from": 0.75,
"to": 1,
"band": "High Propensity"
}
]
}
Once you’ve completed your mapping, click Activate.
Your plugin will now be active, and you will see new palette options for Vidora within your Feature and Request Rules.
NOTE: In V3 there is a known error when saving and activating a plugin configuration. You will receive an error message stating that the plugin configuration was unable to be saved. This is a front end bug, and refreshing your Plugins page (Settings > Plugins) will show the plugin as Enabled.
Using Vidora within Rules
Once activated, you will find a new palette option for both Feature and Request Rules.
Under the Vidora section, you will find decision nodes for the following options:
Vidora Known – Allows you to select a Pipeline, pulled from Vidora. When set, this will tell you whether a user has any data for a particular pipeline – e.g. Anonymous to Registered.
Vidora Percentile – Allows you to select a Pipeline, pulled from Vidora, and a Percentile. For example, checking for users who are part of the 95th percentile for a particular pipeline.
Vidora Score – Allows you to select a Pipeline, pulled from Vidora, a Comparison and a Score. This option is for legacy use of Vidora Scores. For example, checking for users with a score greater than or equal to 0.47985.
Vidora Score Band – Allows you to select a Pipeline, pulled from Vidora, and a Score Band, based on the mappings set in the configuration above. Note, for this to work the mapping must include the correct pipeline id.
To use any of these options within a rule, simply drag them onto the rule canvas like normal, and connect them in the appropriate place, then save and publish your rule.