Ashley Stirrup

A two-point lift in close rate sounds like a rounding error. At Ford Credit, it's the number that turned skeptics into advocates. I sat down with Geoffrey Bell and we talked about how connecting an online test to an offline car sale changed who took experimentation seriously. For a long time, Ford Credit's online experiments stopped at the click. A test could move page views, but no one could say whether it sold a car. That changed when his team learned to connect an online experiment to the offline purchase that followed at the dealership. Control closed at 30 percent, treatment at 32 percent. On a business that size, that two-point gap is not a rounding error. Suddenly experimentation wasn't a data team hobby. It was a lever on the number the business actually runs on. Tie your tests to the metric leadership already cares about, and skeptics turn into advocates fast. What's the one downstream number that would make your experiments impossible to ignore?