📄️ Machine learning models overview
Overview of MessageGears machine learning models for propensity, churn, lifetime value, engagement, product recommendations, and send time and channel optimization (STO), with links to model guides and data input requirements.
📄️ Product recommendation
The Product recommendation model discovers relationships between products through a technique called collaborative filtering.
📄️ Engagement index
The purpose of MessageGears’ Engagement Index model is to predict your customers' likelihood to engage with your brand.
📄️ Second purchase propensity
This classification model scores all active customers in the population on their likelihood to make a second purchase at the time of their first purchase. This model gives you insight into who is most likely to return to your business, and the ability to segment your audience accordingly.
📄️ Send time, day, and channel optimization
MessageGears ML models for send time optimization (STO), optimal day, and best channel (next best channel), including output fields, training data requirements, and delivery integration.
📄️ Purchase propensity
This classification model scores all customers in the population on their likelihood to make a purchase within a given window of time.
📄️ Customer lifetime value
This regression model provides the value of each customer in a given window of time in your customer population.
📄️ Propensity to churn
This classification model scores all customers on their likelihood to churn out of your active customer population. Churn is defined as a customer not making a purchase within a specified window.
📄️ Data input schemas
Each of our models require different data inputs to train the models and score the target populations. The following tables outline the events we use to gather that data.
📄️ Using predictive models in campaigns and journeys
How to apply MessageGears' predictive models directly in campaign and journey configuration, as a channel-selection option and as segmentation criteria.
📄️ Reserved predictive model column names
Reference for the reserved column names, data types, and value ranges of the seven predictive models available as segmentation criteria in Blueprints and journeys.