ABSTRACT
This chapter argues that the ability to run price experiments is a key benefit of online pricing. However, realizing this advantage requires a structured method for designing, running, and evaluating pricing experiments. It requires statistical sophistication to accurately evaluate results in the face of cannibalization. Furthermore, to avoid biases, the group designing, running, and interpreting experiments should be separate from those who have a stake in their outcomes. For these reasons, companies that plan on running multiple pricing experiments should develop an internal science-led group to manage the design and execution of the experiments as well as the validation of the experimental results.
