Vidora provides a Machine Learning (ML) platform for Marketing, AdTech, and Product teams to transform user data into automated decisions to optimize the customer journey. An integration between mParticle and Vidora allows anyone to quickly build ML pipelines and send the predictions back to mParticle as intelligent attributes within your customer profiles, ultimately enabling smarter targeting for more data-driven customer interactions.
Complete steps 1-6 found in the Event documentation of the mParticle-Vidora connection before proceeding here. Complete the below steps before continuing onto step 7 found in the Event documentation.
$intelligent_attribute:cortex:[pipeline name]__score
and $intelligent_attribute:cortex:[pipeline name]__percentile
, where score represents the prediction itself (e.g. conversion probability for a Future Events pipeline, predicted value for a Regression pipeline, etc). These attributes will be visible in mParticle’s Data Master > Catalog.After completing these three steps, continue with step 7 found in the Event documentation.
The sample JSON below illustrates the payload that might be sent from Vidora to mParticle if results were exported from a Machine Learning Pipeline configured to predict each customer’s likelihood to purchase. The payload includes two attributes per customer: (1) conversion probability (the probability that the customer purchases) and (2) percentile (how this customer’s purchase probability ranks relative to all other customers).
{
"environment": "production",
"user_attributes": {
"$intelligent_attribute:cortex:likelihood_to_purchase__score": 0.171425,
"$intelligent_attribute:cortex:likelihood_to_purchase__percentile": 0.879432
},
"mpid": 123456789
}
Was this page helpful?