Quantcast Corporation

Webtrends Corporation

Peter William Kassakian

Daniel Ciprian Preda

Matthew Esch

Separate models are built to predict the likelihood of conversion based on the presence or absence of one or more features. For example, a first model may be built to predict the likelihood of conversion of a non-converter who has never visited an advertiser's website before and a second model may be built to predict the likelihood of conversion of a non-converter who has visited an advertiser's website before. To determine which model to apply to an entity, the consumption history of the entity is searched for the presence or absence of the one or more features used to separate the models. The entity's consumption history is then scored based on the applicable model to determine the likelihood of conversion.

Separation of models based on presence or absence of a feature set and selection of model based on same

A machine-controlled method can include estimating expected conversion rates for ads by applying an estimated conversion rate statistical model to each ad, estimating an expected AOV for each ad by applying an estimated AOV statistical model to each ad, applying an inference algorithm, and determining auction bids based on the estimated expected conversion rate and the estimated expected AOV for the ads.

Growing community of inventors

South San Francisco, CA, United States of America

Peter William Kassakian