Abstract:
|
Online services need to understand how product decisions affect their users. Product changes will often cause an immediate change in user behavior and this is what most A/B tests will measure. However, there is often longer term effect as users learn new behaviors in reaction to the change. Accurately measuring these long term effects is critical to properly understanding how to make the best products. We present an extension to earlier work that further explores how Google search ads affect our users. We compare user learning at different dosage levels, over very long time periods, and user product usage learning.
|