Designing for Behavior Change: Applying Psychology and Behavioral Economics

Behavioral Science

Google Analytics 360 package does provide individual-level data, as do Heap, Adobe Analytics,

Determine the largest viable effect (LVE). What is the largest change in the outcome that you’d expect the intervention to have?

Benchmark the impact your product has on an intermediate user behavior that you can measure regularly, even though it isn’t the final real-world outcome you really care about. Determine how to accurately measure the real-world outcome at least once. Build a bridge between the intermediate user behavior you measure regularly and the real-world outco

A randomized control trial is simply the most effective and rigorous tool out there for determining the impact of your product or communication on behavior. It provides the clearest and most unambiguous signal of impact.

Google Optimize 360, Adobe Target, Optimizely, VWO, and Mixpanel. Many

behavioral metrics are part of the product itself, not an add-on for later.

multiarmed bandits,

you’ll need access to raw, per-person data for statistical modeling.