Robust label attribution for real-time bidding

Bompaire, Martin; Désir, Antoine; Heymann, Benjamin

doi:10.48550/arxiv.2012.01767

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…each conversion must be attributed to a shown ad. This attribution problem is very complex as there usually are several ads displayed in the few hours preceding each conversion (Bompaire, Gilotte, and Heymann 2021;Bompaire, Désir, and Heymann 2021;Ji and Wang 2017;Dalessandro et al 2012). It causes fundamental problems in the estimation of the causal effects and makes the bid by bid optimization extremely difficult in practice.…”

Section: Introductionmentioning

confidence: 99%

Maximizing the Success Probability of Policy Allocations in Online Systems

Betlei,

Vladimirova,

Sebbar

et al. 2024

AAAI

View full text Add to dashboard Cite

The effectiveness of advertising in e-commerce largely depends on the ability of merchants to bid on and win impressions for their targeted users. The bidding procedure is highly complex due to various factors such as market competition, user behavior, and the diverse objectives of advertisers. In this paper we consider the problem at the level of user timelines instead of individual bid requests, manipulating full policies (i.e. pre-defined bidding strategies) and not bid values. In order to optimally allocate policies to users, typical multiple treatments allocation methods solve knapsack-like problems which aim at maximizing an expected value under constraints. In the specific context of online advertising, we argue that optimizing for the probability of success is a more suited objective than expected value maximization, and we introduce the SuccessProbaMax algorithm that aims at finding the policy allocation which is the most likely to outperform a fixed reference policy. Finally, we conduct comprehensive experiments both on synthetic and real-world data to evaluate its performance. The results demonstrate that our proposed algorithm outperforms conventional expected-value maximization algorithms in terms of success rate.

show abstract

Section: Introductionmentioning

confidence: 99%