What is CPC algorithm?
CPC algorithm is the end-to-end data science solution to run click-driven campaigns on RTB. These Campaigns are called CPC campaigns. The function of the CPC Algorithm is to generate bid values to be used in RTB which will lead to achieving the campaign objectives of CPC at scale.
What are the main components of CPC algorithm / How CPC campaigns are optimized?
There are 2 components in the CPC algorithm.
- Prediction Model
- Auto blacklisting Tool
How does the Prediction Model work?
Prediction Model is a logistic regression model trained to predict probability of click given a set of variables associated with every bid request. Prediction Model uses publisher side, advertiser side and user side features in the model.
Bidder computes the bid value as follows :
Bidvalue(privatevalue) = Probability_from-model(click given feature values) * targetCPC
If the predicted probabilities are close to accurate, this will ensure that we always achieve target CPC.
What is Auto Blacklisting Tool?
Auto Blacklisting tool is a safety net on top of model. This tool identifies loss making apps and blacklists them. It identifies loss making apps by a probability model. The tool defines a prior distribution for loss (or profit) of every (app, campaign) combination. At regular intervals it computes the probability that loss > 0 (the probability that the app is a loss making app).
Blacklisting rule: blacklist if probability (loss>0) > 0.9. This ensures that an app gets blacklisted only if there is sufficient data to conclude that it is a loss making app. Once there is sufficient data, tool avoids any further losses by immediately blacklisting the app if found to be loss making.