In Part 1 of this series, I said that in real-time bidding, we should “bid truthfully”, i.e. that you should bid whatever it is worth to you to win. To compute this truthful value, given a target cost per action (CPA) for a campaign, I said you could just multiply that target by the computed probability of seeing an action after the impression, and that would give you your bid value.
I added that by calculating an expected cost of winning an auction, you could compute the expected surplus for that auction and that to pace your spending efficiently, you would only bid truthfully when this expected surplus was above some threshold value, and not bid otherwise. This threshold value would be the output of a closed-loop pace control system (described in Part 0) whose job it is to keep the spend rate close to some target.
In Part 3 of this series, I then showed that in fact, the second claim of Part 1 was not optimal and that instead of setting an expected surplus threshold, you should set an expected return-on-investment (ROI) threshold.
In this post, Part 4 of the series, I show that the meaning of “bidding truthfully” can be slipperier than...
September 16th, 2013 was our Annual Datacratic Day. The day started with a companywide update over coffee and croissants, and then we headed outside to board our rented school bus for a little adventure.
In this post, I show that in order to maximize the economic surplus over a whole campaign, the quantity you should look at on an auction-by-auction basis to decide when to bid is actually the expected return on investment (ROI) rather than the expected surplus. At Datacratic, we actually switched to an ROI-based strategy about a year ago but I didn’t get a chance to follow up with a blog post until now.
At Datacratic, one of the product we offer our customers is our real-time bidding (RTB) optimisation that can plug directly into any RTBKit installation. We’re always hard at work to improve our optimisation capabilities so clients can identify valuable impressions for their advertisers. Every bid request is priced independently and real-time feedback is given to the machine learning models. They adjust immediately to changing conditions and learn about data they had not been exposed to during their initial training.
Today is an exciting day for Datacratic and, we hope; an exciting day for the real-time advertising ecosystem. We hope it marks a significant milestone in the evolution of big data and real-time marketing. Today is the day that we have released the first iteration of RTBkit, an open source software framework which makes it easy to create a scalable real time bidder for use on advertising exchanges.