Predictive Studio - Score Definition

Creating a Predictive Score definition

Blueshift’s Predictive Studio allows you to define and customize a Predictive Score based on your Marketing objective. The underlying AI model learns a user’s likelihood (Predictive Score) to convert on specific events in the future, based on past behaviors.




Goal events -  Events for which that you’d like to create a Predictive Score. Presence of at least one of these events will be counted as a conversion. For example - purchase, subscription_renewal, etc. You can choose any events that you are tracking with Blueshift.  You can read more on events here.


Prediction windowPredictions will be made and remain valid for this time period. For example - predict purchase intent in the next 7 days, subscription renewal in the next 30 days.

The default is 7 days. Shorter windows(a day or few days) could lead to more accurate predictions, while longer windows could introduce noise/irregularities, which leads to lower predictive accuracy.

Consider setting this value such that the historical conversion rate.  ( i.e i number of conversion in prediction window/number of active users in lookback days * 100) is at least 1%.


Lookback daysAudience for the Predictive Scores will include those users who had at least one impression(event or campaign action) in the lookback period. Default - 30 days (i.e monthly active users). This input shall be equal to the length of the conversion funnel. In most use cases, the conversion is heavily correlated with the recent engagement, so 30 days(monthly) or 90 days(quarterly) usually suffices.

E-commerce funnels are usually short, so 7-14 days work for most e-commerce purchase intent use cases. Subscription businesses can set this input based on their billing cycles to predict subscription churns.

Consider setting this value such that the historical conversion rate ( i.e number of conversion in prediction window/number of active users in lookback days * 100) is at least 1%.


[Optional] Custom user attributes -  Include user demographics (i.e. age, location, etc), preferences(categories of interest such as genres, topics, artists, venues, etc), memberships( subscription type) and lifetime attributes(lifetime orders, revenues, etc). We use the latest value of custom user attributes.  Warning: Be careful and don’t pick a user attribute which is updated as a result of the conversion.  Otherwise this would cause leakage(overfitting) and the model wouldn’t generalize well on unseen data. An example of one such user attribute is “total_orders” for predicting purchase conversions, if we increment total_orders after conversion. For one-time purchasers, the model could confidently learn a simple rule that users who convert must have total_orders>0, which is not what we want.



Click here for more details on custom user attributes.


[Optional] Custom user attributes filters - If user behaviors or event tracking varies by demographics, we might want to create a separate model for each demographic cohort. In that case, user attribute segment filters can be chosen. For example, create Predictive Scores for users whose home_country is “US” and lifetime_orders > 0. AND/OR rules can be combined.



[Default] Blueshift User attributes - The following list of Blueshift’s derived attributes are included here by default:














See the following article for more details on Blueshift’s user attributes.


[Default] Modeling frequency - Weekly, every Sunday UTC midnight.

[Default] Scoring frequency - Daily, every UTC midnight

[Default] Funnel events: Events which precede and lead to the conversion.

For example:

1) product views, favorites, add to carts for purchase conversion.

2) content viewed, billing changes, login, payment notification for subscription renewal conversion. Blueshift determines the funnel events by default.

[Default] Campaign actions - open and click activity on campaigns originating from Blueshift




Data requirements

The most important thing while setting up a Predictive Score is ensuring that the historical conversion rate, ( i.e number of conversions in prediction window/size of the modeled audience * 100), is at least 1% and at least 1,000+ users have converted in the past prediction window. The AI model learns to make predictions based on historical conversions. Too few conversions or very low conversion rates may lead to low performance or stats resulting in insignificant model. 

If data requirements are not met, Predictive Scores will fail and there will be an alert on the studio dashboard. Consider tuning prediction window, goal lookback days, user attribute filters to make it work.

Once data requirements are met, an AI model will be created. AI Model summary details are talked about in the Model Viz section.


A Predictive Score between 0-100 is generated for every user in the scoring audience. The Predictive Scores are available on customer profiles, which can be used for lookups, segmentation, syndications and exports.


Can I choose a goal based on an event attribute, like product sku?

Yes, the studio doesn’t support this option yet, but we can customize the goal inputs on the backend. Currently, we support goal event filters on product attributes(i.e category, brand, sku) if product sku is available on the event.

Can I filter my audience based on event counts and event attributes?

Yes, the studio doesn’t support this option yet, but we can customize filters on the backend. Currently, we support event filters based on event count(e.g number of purchase > 0), event recency(e.g last purchase < 7 days) and product attributes(e.g category, brand, sku) if product sku is available on the event.

Was this article helpful?
0 out of 0 found this helpful