Optimal Real-Time Bidding for Display Advertising

Optimal Real-Time Bidding for Display Advertising

In this talk we present our study of optimal bidding strategies for Real-Time Bidding (RTB) in display advertising. RTB allows advertisers to bid on a display ad impression in real time when it is being generated. It goes beyond contextual advertising by motivating the bidding focused on user data and it is different from the sponsored search auction where the bid price is associated with keywords. For the buyer side, a fundamental technical challenge is to automate the bid process based on their budget, the campaign objective and various information gathered in real-time and in history. The talk is split into 3 parts: 1) The theoretical analysis where the programmatic bidding is cast as a functional optimisation problem. Under certain dependency assumptions, we derive simple bidding functions that can be calculated in real time. Our findings show that the optimal bid has a non-linear relationship with the impression level evaluation such as the click-through rate and the conversion rate, which are estimated in real time from the impression level features. This is different from previous work that is mainly focused on a linear bidding function. Our mathematical derivation suggests that optimal bidding strategies should try to bid more impressions rather than focus on a small set of highly valued impressions. Indeed, according to the current RTB market data, compared to the higher evaluated impressions, the lower evaluated ones are more cost effective and the chances of winning them are relatively higher. Aside from the theoretical insights, offline experiments on a real dataset and online experiments on an operational RTB system verify the effectiveness of our proposed optimal bidding strategies and the functional optimisation framework. 2) Our experience of participating the iPinyou Global Bidding Competition in 2013 and winning the 1st prize of the 3rd season. We will talk about the offline algorithms and online adaptations, as well as some interesting findings from practice. The analysis of the iPinyou RTB dataset. This dataset contains logs from three seasons’ offline stage. We will talk about the background, format, and accessibility of the dataset and discuss its characteristics. .

source

Leave a Reply

%d bloggers like this: