A Centre of Excellence delivering next generation AI Research and Training at the service of Media, Society and Democracy.
In the InPreVi project, as marketers, company main goal is to generate as much benefit and impact as possible by optimizing the video marketing campaigns for our clients. Therefore, it is critical to ensure that the web traffic (clicks) and video content are perfectly aligned between them and the client business. For that reason, the core research in this project will be focused on the identification of the inauthentic traffic patterns and the prediction of the campaign quality so the account managers will have a tool for budget investment optimization and ROI increase.
This market motivation is aligned with challenge 5 of the Open Call (Evidence Collection in Digital Media Authentication) to identify is a user (web traffic) clicking in an ad is authentic or inauthentic.
To do so, JOT will cover all the expected evidence:
(a) Explanation in fact check stories: AI models and traffic validation will be applied to JOT video marketing campaigns, using historical data base to train the prediction services.
(b) “Debunking” reports/databases: Inauthentic traffic detection will allow the identification of action patterns, locations, and fraudulent traffic sources.
(c) Verification processes: Models and prediction services will be validated and verified thanks to the historical database currently existing in JOT.
(d) Legal proceedings: JOT is proprietary of all the data used in this case and no sensitive nor personal data is processed.
(e) Cases involving personal identities: InPreVi will allow the identification of robot pattern for invalid traffic generation. This service will not interfere in human being actions..
This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 951911.