Likelihood of an Event

Propensity to Event model can be used to predict the likelihood of an event happening in the future. You can use the model to predict the probability of a user taking a specific action, such as making a purchase, clicking on an ad, or subscribing to a service.

The Propensity to Event model utilizes multiple data points to generate the prediction:

• previous actions of the user: product views, purchases, etc.
• previous actions of other users
• user profile data (when available)
• contextual data: time of day, day of the week, etc.

The propensity model can capture complex patterns in the data and make predictions based on the user's behavior and preferences. It is also using attention mechanisms, which allow the model to focus on the most relevant data points when making predictions.

Getting propensity predictions

1. Create a propensity model in the Almeta Cloud console to get a model ID.
2. Query a web tag calculation or API endpoint to get the propensity predictions.

Query format

_almeta.t('calculate', {
	model_id: MODEL_ID, // replace with your model ID
});

// Alternatively, you can use await when the web tag is fully loaded
var prediction = await _almeta.calculate({
    model_id: MODEL_ID,
});

Data Point	Description
model_id (required)	Unique identifier for the propensity model (obtained from Almeta Cloud console).

Common use cases

Propensity to Event model can be used in various scenarios to predict the likelihood of an event happening in the future.

Propensity to Purchase

Predict the likelihood of a user making a purchase based on their previous purchases and behavior on your website.

Propensity to Churn

Predict the likelihood of a user unsubscribing from your service based on their usage patterns and interactions with your product.

Propensity to Watch a Video

Predict the likelihood of a user watching a video to a specific point based on their viewing history and preferences.

Propensity to Click on an Email

Predict the likelihood of a user clicking on an email based on their previous interactions with your email campaigns and website.