An analytical solution to the budget-pacing problem in programmatic advertising

Fernandez-Tapia, Joaquin

doi:10.1080/02522667.2017.1303946

Cited by 14 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the communication ecosystem, programmatic advertising is seen as a disruptive element as it has lowered the costs and risks of mass advertising that have often been criticised, presenting a more cost-effective way of advertising and providing a competitive advantage for those organisations that manage to understand their ecosystem (Fernandez-Tapia, 2019).…”

Section: Conceptual Framework and Hypothesesmentioning

confidence: 99%

The role of perceived usefulness and annoyance on programmatic advertising: the moderating effect of Internet user privacy and cookies

Barriopedro

Valiño

Mansori-Amar

2022

CCIJ

View full text Add to dashboard Cite

PurposeThe study of the background to programmatic advertising is of great interest in the context of digital marketing. Therefore, the main aim of this research is to define a structural equation modelling (SEM) model, which allows studying the relationship between the usefulness and privacy of online ads to increase the effectiveness and efficiency of campaigns through the use of computation and big data.Design/methodology/approachA cross-sectional descriptive study based on the Web Browsers Survey was carried out on a sample of 24,062 Internet users by the Association for Media Research. The partial least squares structural equation modelling method (PLS-SEM) was applied to evaluate the model with the study constructs and test the hypotheses.FindingsThe result of this research allows us to know how perceived usefulness (U) and perceived annoyance (A) affect users' privacy concerns (P) and concerns about the storage and use of their data through cookies (C). The authors also seek if there is any relationship between privacy concerns (P) and cookies (C) on users' level of Internet usage (IU).Originality/valueOne of the novelties of this study is the consideration not only of Internet user perceptions but also their concerns about privacy and the use of cookies, as key variables in the strategic management of the use of programmatic advertising in digital marketing.

show abstract

Section: Conceptual Framework and Hypothesesmentioning

confidence: 99%

The role of perceived usefulness and annoyance on programmatic advertising: the moderating effect of Internet user privacy and cookies

Barriopedro

Valiño

Mansori-Amar

2022

CCIJ

View full text Add to dashboard Cite

show abstract

“…The idea that showing several displays in a row does not serve the advertiser well is at the origin of several works on pacing and probabilistic throttling. While an analytical solution of the pacing problem for display advertising is presented in [Fernandez-Tapia, 2019], most industrial solutions rely on heuristics [Agarwal et al, 2014, Chen et al, 2011, Lee et al, 2013, Xu et al, 2015.…”

Section: Related Work and Contributionmentioning

confidence: 99%

Causal Models for Real Time Bidding with Repeated User Interactions

Bompaire

Gilotte

Heymann

2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

A large portion of online advertising displays are sold through an auction mechanism called Real Time Bidding (RTB). Each auction corresponds to a display opportunity, for which the competing advertisers need to precisely estimate the economical value in order to bid accordingly. This estimate is typically taken as the advertiser's payoff for the target event -such as a purchase on the merchant website attributed to this display -times this event estimated probability. However, this greedy approach is too naive when several displays are shown to the same user. The purpose of the present paper is to discuss how such an estimation should be made when a user has already been shown one or more displays. Intuitively, while a user is more likely to make a purchase if the number of displays increases, the marginal effect of each display is expected to be decreasing. In this work, we first frame this bidding problem with repeated user interactions by using causal models to value each display individually. Then, based on this approach, we introduce a simple rule to improve the value estimate. This change shows both interesting qualitative properties that follow our previous intuition as well as quantitative improvements on a public data set and online in a production environment.

show abstract

“…(1) Recompute click probabilities with the new index values, 2 We are unable to give the exact set of features due to company policy. 3 Embeddings could be used to represent entities towards implicit personalization.…”

Section: Post-ranking Calibration For Estimating Click Probabilitiesmentioning

confidence: 99%

“…The next step in the marketplace mechanism is to understand whether the retrieved jobs are able to spend their daily budgets comfortably according to a preset plan. While the details of how to compute this spending plan [2,8] is out of our scope, one can utilize different metrics to distribute the jobs daily budget throughout different hours. For example, a job might decide to try spending 40% of its budget between 10am-12pm if more job seekers (whose skills match the job) come to the system during that period.…”

Section: Introductionmentioning

confidence: 99%

Impression Pacing for Jobs Marketplace at LinkedIn

Geyik

Chowdhury

Raudies

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

The goal of Jobs Marketplace at LinkedIn is to match members to promoted job postings such that both job posters' ROI is optimized (amount of money spent per job clicks and applications) and the members are presented with relevant jobs that they are interested in and qualified for. This is achieved via a first-price auction mechanism where each job provides a bid for the member that comes to the job recommendations page. This bid depends on the match of the member to the job, as well as the daily budget that remains for the job, and its capability to spend it via clicks (e.g. some jobs might have more demand and have it easier to spend their budgets via clicks than others). In such a scheme, budget pacing, i.e. the capability of a job to spend its daily budget evenly, or according to a preset plan, is extremely important towards efficient utilization of its budget via reaching a higher number of candidates, and obey a variety of spending plans optimizing for different events such as clicks and applications. In this paper, we propose an impression-based spend computation system, hence an impression-based pacing scheme. This approach works via assigning a projected/expected charge amount each time a job is shown to the user, taking into account both the likelihood that the user will click the job, and the recommender system specific considerations such as the order within a page that a job is recommended. The results of our alternate-day test shows that such a scheme leads to a smoother spending and improved adherence to the planned spend, and increases secondary metrics such as job clicks and applications.

show abstract

An analytical solution to the budget-pacing problem in programmatic advertising

Cited by 14 publications

References 3 publications

The role of perceived usefulness and annoyance on programmatic advertising: the moderating effect of Internet user privacy and cookies

The role of perceived usefulness and annoyance on programmatic advertising: the moderating effect of Internet user privacy and cookies

Causal Models for Real Time Bidding with Repeated User Interactions

Impression Pacing for Jobs Marketplace at LinkedIn

Contact Info

Product

Resources

About