PROJECT TITLE :

Probabilistic Models For Ad View ability Prediction On The Web - 2017

ABSTRACT:

On-line show advertising has becomes a billion-greenback trade, and it keeps growing. Advertisers try to send selling messages to attract potential customers via graphic banner ads on publishers' webpages. Advertisers are charged for every view of a page that delivers their show ads. But, recent studies have discovered that additional than [*fr1] of the ads are never shown on users' screens thanks to insufficient scrolling. Thus, advertisers waste a great amount of money on these ads that don't bring any come back on investment. Given this case, the Interactive Advertising Bureau concerns a shift toward charging by viewable impression, i.e., charge for ads that are viewed by users. With this new pricing model, it is useful to predict the viewability of an advertisement. This paper proposes 2 probabilistic latent class models (PLC) that predict the viewability of any given scroll depth for a user-page try. Using a real-life dataset from a giant publisher, the experiments demonstrate that our models outperform comparison systems.