Over the last decade, digital media (web or app publishers) generalized the use of real time ad auctions to sell their ad spaces. Multiple auction platforms, also called Supply-Side Platforms (SSP), were created. Because of this multiplicity, publishers started to create competition between SSPs. In this setting, there are two successive auctions: a second price auction in each SSP and a secondary, first price auction, called header bidding auction, between SSPs.In this paper, we consider an SSP competing with other SSPs for ad spaces. The SSP acts as an intermediary between an advertiser wanting to buy ad spaces and a web publisher wanting to sell its ad spaces, and needs to define a bidding strategy to be able to deliver to the advertisers as many ads as possible while spending as little as possible. The revenue optimization of this SSP can be written as a contextual bandit problem, where the context consists of the information available about the ad opportunity, such as properties of the internet user or of the ad placement.Using classical multi-armed bandit strategies (such as the original versions of UCB and EXP3) is inefficient in this setting and yields a low convergence speed, as the arms are very correlated. In this paper we design and experiment a version of the Thompson Sampling algorithm that easily takes this correlation into account. We combine this bayesian algorithm with a particle filter, which permits to handle non-stationarity by sequentially estimating the distribution of the highest bid to beat in order to win an auction. We apply this methodology on two real auction datasets, and show that it significantly outperforms more classical approaches.The strategy defined in this paper is being developed to be deployed on thousands of publishers worldwide.

This paper describes an engine to optimize web publishers revenue from second-price auctions, which are widely used to sell online ad spaces in a mechanism called real-time bidding. This problem is crucial for web publishers, because setting appropriate reserve prices can increase significantly their revenue.We consider a practical setting where the only available information before an auction occurs consists of a user identifier and an ad placement identifier. Once the auction has happened, we observe censored outcomes : if the auction has been won (i.e the reserve price is smaller than the first bid), we observe the first bid and the closing price of the auction, otherwise we do not observe any bid value.The engine predicts an optimal reserve price for each auction and is based on two key components: (i) a non-parametric regression model of auction revenue based on dynamic, timeweighted matrix factorization which implicitly builds adaptive users' and placements' profiles; (ii) a non-parametric model to estimate the revenue under censorship based on an on-line extension of the Aalen's Additive Model.An engine very similar to the one described in this paper is applied to hundreds of web publishers across the world and yields a very significant revenue increase. The experimental results on a few of these publishers detailed in this paper show that it outperforms state-of-the-art methods and that it tackles very efficiently the censorship issue.

In this paper, we consider the problem of optimizing the revenue a web publisher gets through real-time bidding (i.e. from ads sold in real-time auctions) and direct (i.e. from ads sold through contracts agreed in advance). We consider a setting where the publisher is able to bid in the real-time bidding auction for each impression. If it wins the auction, it chooses a direct campaign to deliver and displays the corresponding ad.This paper presents an algorithm to build an optimal strategy for the publisher to deliver its direct campaigns while maximizing its real-time bidding revenue. The optimal strategy gives a formula to determine the publisher bid as well as a way to choose the direct campaign being delivered if the publisher bidder wins the auction, depending on the impression characteristics.The optimal strategy can be estimated on past auctions data. The algorithm scales with the number of campaigns and the size of the dataset. This is a very important feature, as in practice a publisher may have thousands of active direct campaigns at the same time and would like to estimate an optimal strategy on billions of auctions.The algorithm is a key component of a system which is being developed, and which will be deployed on thousands of web publishers worldwide, helping them to serve efficiently billions of ads a day to hundreds of millions of visitors.

Bidding in real-time auctions can be a difficult stochastic control task; especially if underdelivery incurs strong penalties and the market is very uncertain.Most current works and implementations focus on optimally delivering a campaign given a reasonable forecast of the market. Practical implementations have a feedback loop to adjust and be robust to forecasting errors, but no implementation, to the best of our knowledge, uses a model of market risk and actively anticipates market shifts.Solving such stochastic control problems in practice is actually very challenging. This paper proposes an approximate solution based on a Recurrent Neural Network (RNN) architecture that is both effective and practical for implementation in a production environment. The RNN bidder provisions everything it needs to avoid missing its goal. It also deliberately falls short of its goal when buying the missing impressions would cost more than the penalty for not reaching it.

The big-data revolution announced ten years ago [MCB + 11] does not seem to have fully happened at the expected scale [Ana16]. One of the main obstacle to this, has been the lack of data circulation. And one of the many reasons people and organizations did not share as much as expected is the privacy risk associated with data sharing operations.There has been many works on practical systems to compute statistical queries with Differential Privacy (DP). There have also been practical implementations of systems to train Neural Networks with DP [MAE + 18, YSS + 21], but relatively little efforts have been dedicated to designing scalable classical Machine Learning (ML) models providing DP guarantees.In this work we describe and implement a DP fork of a battle tested ML model: XGBoost. Our approach beats by a large margin previous attempts at the task, in terms of accuracy achieved for a given privacy budget. It is also the only DP implementation of boosted trees that scales to big data and can run in distributed environments such as: Kubernetes, Dask or Apache Spark.