DeepAI AI Chat
Log In Sign Up

Challenges and approaches to privacy preserving post-click conversion prediction

by   Conor O'Brien, et al.

Online advertising has typically been more personalized than offline advertising, through the use of machine learning models and real-time auctions for ad targeting. One specific task, predicting the likelihood of conversion (i.e. the probability a user will purchase the advertised product), is crucial to the advertising ecosystem for both targeting and pricing ads. Currently, these models are often trained by observing individual user behavior, but, increasingly, regulatory and technical constraints are requiring privacy-preserving approaches. For example, major platforms are moving to restrict tracking individual user events across multiple applications, and governments around the world have shown steadily more interest in regulating the use of personal data. Instead of receiving data about individual user behavior, advertisers may receive privacy-preserving feedback, such as the number of installs of an advertised app that resulted from a group of users. In this paper we outline the recent privacy-related changes in the online advertising ecosystem from a machine learning perspective. We provide an overview of the challenges and constraints when learning conversion models in this setting. We introduce a novel approach for training these models that makes use of post-ranking signals. We show using offline experiments on real world data that it outperforms a model relying on opt-in data alone, and significantly reduces model degradation when no individual labels are available. Finally, we discuss future directions for research in this evolving area.


page 1

page 2

page 3

page 4


Towards a User Privacy-Aware Mobile Gaming App Installation Prediction Model

Over the past decade, programmatic advertising has received a great deal...

Reacting to Variations in Product Demand: An Application for Conversion Rate (CR) Prediction in Sponsored Search

In online internet advertising, machine learning models are widely used ...

Revenue Attribution on iOS 14 using Conversion Values in F2P Games

Mobile app developers use paid advertising campaigns to acquire new user...

Measuring ad value without bankrupting user privacy

Recent work has demonstrated that by monitoring the Real Time Bidding (R...

Learning from Multi-User Activity Trails for B2B Ad Targeting

Online purchase decisions in organizations can go through a complex jour...

Cross-Device Tracking: Systematic Method to Detect and Measure CDT

Online advertising, the backbone of the free Web, has transformed the ma...

Beyond content analysis: Detecting targeted ads via distributed counting

Being able to check whether an online advertisement has been targeted is...