A.I. Quality Prediction

What it is about

Running Lead or Mobile CPI campaigns always requires regular ROI checks to ensure that users actually convert into paying customers. For this marketing experts typically use Goals to measure user activity or purchases. When a new campaign starts, marketers have to wait typically 2 weeks until they can see first results to determine the quality of the source what can become time consuming and costly.

With quality predictions you can get a better indication on the first day of the campaign.

Using our trained A.I. models, you can find out how likely a conversion is to turn into a goal.

From our internal analytics of sources for fraud reasons, we have discovered that quality of users also depends on a variety of factors such as:

• day of the week,
• if a VPN is used,
• how long it took the user to complete a survey or install an APP, 
• the Device,
• OS Version
• and many other factors.

The impact of each factor on achieving a goal is too complex to put it in a fixed set of rules. That is why we started training an A.I model based on 7.5 mio conversions and comparing the outcome of each single conversion to turn into a paying customers. 

The results are predictions and dot not represent a perfect accuracy. Prediction scoring is meant as another tool for marketers to decide early in the campaign whether they want to continue running the campaign at high volume or if they better reduce volume or pause the campaign to see definite results after 2 weeks. 

How to activate the Quality Prediction

1. Find your integration and go to Setup

2. Go to 'A.I. Prediction' and choose a model:

• Optimised for Mobile CPI Traffic
• Considers time of day, day of the week, ISP, Device, timezone, language and other factors)
• You will see a score for conversions of mobile devices.

3. Save your choice

4. Go to the Conversion Report or the Fraud Report and add the column 'A.I. Score'. Now you can see the results.