With respect to relevancy and interestingness, what’s your criteria for approving advertiser and publisher? If I have a nascent product of uncertain interestingness, can I still be accepted as an advertiser?
> Next, we built a crawler that indexes the sites on our network to help target our ads. Using an ML classifier (built with SpaCy), it can tell if a page is about data science or about full stack development. This allows advertisers to target the niche they are focused on and ensure the ads perform well, without doing any user tracking.
This sounds very interesting really. Have you done any tests to compare your method with Google’s user info harvesting method? I would really love to get a more detailed overview on how the whole system works if you’ve written about that somewhere.