OHM SmallData’s mathematical model automatically generates the core of application users, which is a segment of the audience that brings maximum revenue (or generates other target events).
The core of users with the highest paying capacity is automatically uploaded to an advertising system (for example, the Facebook ad system) that generates a segment of similar users and filters out those who have already installed the application.
As opposed to searching for users similar to all those who have made the conversion, the core of users allows for making more accurate forecasts and improving the quality of purchasing.
For applications with typically no conversions in the first two days after installation, increasing the efficiency of AdWords UAC Action campaigns may take a significant amount of time.
The quality of training would be highest if the conversion data is sent to Google within the first 3 days after installation. OHM SmallData has an embedded mathematical model to predict, in 1 or 2 days after installation, a target action of a user within the following 30 days. The model’s precision rate reaches 95% with the recall rate of 75%.
Automatic transmission of data about actual and predicted conversions to AdWords using API ensures quick learning of the advertising system to buy the most valuable audience and helps boosting sales without increasing the cost of a target action.