Real-Time Influence Maximization in a RTB Setting
- PDF / 1,701,526 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 79 Downloads / 195 Views
Real‑Time Influence Maximization in a RTB Setting David Dupuis1 · Cédric du Mouza2 · Nicolas Travers3 · Gaël Chareyron1 Received: 11 March 2020 / Revised: 24 May 2020 / Accepted: 8 June 2020 © The Author(s) 2020
Abstract To maximize the impact of an advertisement campaign on social networks, the real-time bidding (RTB) systems aim at targeting the most influential users of this network. Influence maximization (IM) is a solution that addresses this issue by maximizing the coverage of the network with top-k influencers who maximize the diffusion of information. Associated with online advertising strategies at Web scale, RTB is faced with complex ad placement decisions in real time to deal with a high-speed stream of online users. To tackle this issue, IM strategies should be modified in order to integrate RTB constraints. While most traditional IM methods deal with static sets of top influencers, they hardly address the dynamic influence targeting issue by integrating short time decision, no interchange and stream’s incompleteness. This paper proposes a real-time influence maximization approach which takes influence maximization decisions within a real-time bidding environment. A deep analysis of influence scores of users over several social networks is presented as well a strategy to guarantee the impact of an IM strategy in order to define the budget of an ad campaign. Finally, we offer a thorough experimental process to compare static versus dynamic IM solutions wrt. influence scores. Keywords Real-time bidding · Influence maximization · Social network
1 Introduction Influence maximization (IM) is a trend topic since Kempe et al. [19], known as a maximum coverage problem of social networks. The goal is to find the smallest subset of individuals in a social network, whom when targeted with a piece of information will maximize its diffusion through social influence. Thus, IM aims at maximizing the influence impact of a set of users. “Influence” is “the power of causing an effect in indirect or intangible ways” (Merriam-Webster). In other * Nicolas Travers [email protected] David Dupuis [email protected] Cédric du Mouza [email protected] Gaël Chareyron [email protected] 1
Research Center, Léonard de Vinci Pôle Universitaire, Paris La Défense, France
2
CNAM, Paris, France
3
Research Center and CNAM, Léonard de Vinci Pôle Universitaire, Paris La Défense, France
words, a user can be influenced if he saw the ad, interacted with it, purchased the product or was encouraged to do so in the future. Today, real-time bidding (RTB) outpaced other advertising strategies in terms of online advertising [29, 38] and social network services (SNS). RTB is an online auction system which allows advertisers to bid in real time for ad locations on a Web page loaded by users and thus to target them efficiently. In RTB, advertisers see a stream of users, one at a time and have less than 100 ms [11, 38] to decide to bid or not. The bidders do not know what the auction landscape looks like and conseque
Data Loading...
