Predictive analytics

See how the decisions you make today affect your business in a month, 6 months or 2 years. Predict your future revenue, optimize ad spend and assess your campaign’s future performance just one day after its launch.
Fully automated and ready-to-use LTV forecast

In-app purchases
In-app subscriptions
Ad monetization
Custom revenue
01 Prediction accuracy of up to 90% Predictions are based on millions of user actions and in-app events. An individual set of ML-models is applied to each app. 02 Prediction horizon of up to 2 years See how your decisions today affect your business in 30, 60, 90, 180, 365 or 730 days. 03 All-level prediction Gives an LTV forecast with a breakdown by country, media source or campaign, and can be drilled down to a specific user. 04 Plug-and-play solution
One SDK required
Predictions are available just one day after you launch your ad campaign. Optimize your campaigns from the outset and stop wasting budget.
05 Assess potential revenue from users Forecast revenue to be generated by each user cohort. Target the right audience, minimize costs and acquire more valuable customers. 06 Free LTV forecast based on SKAdNetwork data Predict the LTV of users who came from iOS 14.5+ campaigns, with a prediction horizon of up to 180 days.
Average prediction
How MyTracker's prediction model model copes with sudden changes in revenue generation?
One of the key weaknesses of predictive analytics is the poor ability to factor in qualitative shifts or fluctuations after the bifurcation points. As all these algorithms are based on quantitative probability methods, they face difficulties when it comes to predicting user behaviour after sudden and significant changes.

Say you announced a big discount or promo, resulting in more customers buying your products. Is this only a temporary effect? If yes, when will it be reversed? Will it lead to a higher or lower LTV of an average user?

Predicting such effects is a challenging task for an algorithm, which may produce a less accurate LTV prediction after a successful promo. Another factor likely to impact the analysis is a change in ad monetization or overall app development strategy. The system detects unexpected activity and makes relevant adjustments to models by flattening the peaks. Yet, 100% accuracy cannot be guaranteed in this case.
Will new cohorts be taken into account?
One of the greatest strengths of MyTracker’s model is its ability to predict revenue generation from any group of users. Thanks to the model mix, we are less dependent on historical data for a similar cohort. Even if no historical data is available, the system makes calculations based on user behavior in similar apps.

This means that you can have an accurate estimate for any cross section (by age, sex, country or add campaign).
What about different payment types?
Different types of payments (in-app payments, subscriptions, ad monetization) may vary substantially. Subscription payments can drop, while ad revenues may increase. Their trends may often move independently of each other.

This is why MyTracker employs different approaches to tackle each type of payment. Some of them would need a regression tree model, while for others a simple approximation of the logarithm function works better.
How accurate are MyTracker’s LTV predictions?
MyTracker can predict Lifetime Value (total revenue from a user since app installation) with an accuracy of up to 90% on the 30th, 60th, 90th, 180th, 365th and 730th day of the app installation.
How does MyTracker improve accuracy?
The more data we collect by app, revenue type or other metrics, the more accurate MyTracker's prediction will be. All methods that we use in MyTracker are regularly validated. On top of that, the prediction quality is controlled on an ongoing basis, with some models discarded automatically and others becoming more dominant.
Who is LTV prediction for?
LTV prediction is a valuable marketing tool to analyze apps with in-app purchases or subscriptions and assess revenues by advertising channel and campaign before you spend money on them.
When can you expect to see predictions start working for your app?
Relying on billions of actions, MyTracker models are capable of making up-to-date predictions from the first days of use. As your app data accumulates and the models are trained to adapt to a specific audience, predictions become increasingly accurate.
How to start using LTV predictions in MyTracker?
Integrate MyTracker SDK into your app. More instructions on how to do this are available here.

Go to our Report Builder and select the prediction period in the Metrics → LTV Prediction section.
Do LTV predictions work with SKAdNetwork data?
Yes, they do. We have created a machine-learning model that predicts LTV using SKAN conversions received from Apple. The model generates a forecast based on the payments of organic users and those who gave the ATT consent, while also factoring in CVs. You can learn more about this method and get a step-by-step guidance in our article.
Does MyTracker's predictive model only predict LTV?
MyTracker does not limit itself to LTV predictions: with MyTracker, you can predict user churn and export user IDs with high predicted churn rates. This is a powerful tool to manage churn effectively and with more precision. For example, you can offer premium days to users who are about to quit. For those less likely to leave, a couple of free in-game coins or a simple push notification would probably do the trick.
Boost your projects with MyTracker free solutions