Improving Ads-Profitability Using Traffic-Fingerprints
This addresses the challenge of optimizing ad revenue for online advertisers by enabling better targeting on pages with negligible traffic, representing an incremental improvement in ad-tech methods.
The paper tackled the problem of predicting ad profitability on web pages with low traffic by introducing traffic-fingerprints, 24-dimensional vectors representing daily traffic distributions, and showed that clustering these fingerprints correlates with conversion rates, leading to a revenue increase of over 50% in online campaigns.
This paper introduces the concept of traffic-fingerprints, i.e., normalized 24-dimensional vectors representing a distribution of daily traffic on a web page. Using k-means clustering we show that similarity of traffic-fingerprints is related to the similarity of profitability time patterns for ads shown on these pages. In other words, these fingerprints are correlated with the conversions rates, thus allowing us to argue about conversion rates on pages with negligible traffic. By blocking or unblocking whole clusters of pages we were able to increase the revenue of online campaigns by more than 50%.