Facebook's FBX - a social media real-time bidding (RTB) ad exchange - allows the purchase of ads that retargets users based on past online browsing history. FBX is huge in the real-time bidding space and accounts for a significant number of retargeted clicks on the Web.
FBX key features include:
Millions of ads are bought on FBX every second via demand-side platforms that plug advertisers into FBX. Billions of impressions are served every day. Facebook accounts for about half of retargeted ad clicks.
Real-time bidding is key as it's impossible to target a user who is interested in living room furniture with personalized ads when they open their Facebook page unless he or she can be identified and served a relevant ad in milliseconds.
FBX assists "demand fulfillment" by nudging shoppers to complete a purchase they've already shown interest in.
FBX produces comparatively good results considering cost and performance. FBX platform continually learns and improves. See improving News Feed placements.
FBX is not yet available on mobile and Sponsored Story social-native ads (heart of Facebook's ad ecosystem) aren't accessible via FBX. FBX News Feed ads are still limited in terms of their social features.
See Report: http://bit.ly/1cDQ5XC
Real-time applications have long been considered off-limits for Hadoop clusters and Hadoop is often considered key to open-source exploitation of really large data streams. This talk shows how Storm and Hadoop can work together to achieve latencies of less than 5 ms typically and less than 5 seconds almost certainly can be achieved for a sample metrics application while still retaining years of data with high availability and durability. This is done using a hybrid system where Storm and Hadoop cooperate to do something neither can do alone.