Imagine you are an advertiser working on ad optimization on a website:
- There are three different colors of ad background – red, green, and blue. Which one will achieve the best click-through rate (CTR)?
- There are three types of wordings of the ad – learn …, free ..., and try .... Which one will achieve the best CTR?
For each visitor, we need to choose an ad in order to maximize the CTR over time. How can we solve this?
Perhaps you are thinking about A/B testing, where you randomly split the traffic into groups and assign each ad to a different group, and then choose the ad from the group with the highest CTR after a period of observation. However, this is basically a complete exploration, and we are usually unsure of how long the observation period should be and will end up losing a large portion...
