Behavioral On-Line Advertising

TL;DR

This paper introduces a real-time algorithm for behavioral online advertising that predicts user click probabilities based on actions like clicks and searches, optimizing banner display for maximum engagement or profit.

Contribution

The paper presents a novel real-time algorithm for behavioral targeting that estimates click probabilities and optimizes banner selection for engagement and profit.

Findings

Effective real-time click probability estimation

Improved banner selection for higher engagement

Enhanced profit optimization in online advertising

Abstract

We present a new algorithm for behavioral targeting of banner advertisements. We record different user's actions such as clicks, search queries and page views. We use the collected information on the user to estimate in real time the probability of a click on a banner. A banner is displayed if it either has the highest probability of being clicked or if it is the one that generates the highest average profit.