Personalizing policies can theoretically increase their effectiveness. However, personalization
is difficult when individual types are unobservable, especially when policymaker
and individual preferences are not aligned, causing individuals to misreport their
type. Mechanism design offers a strategy to overcome this issue: offer a menu of policy
choices, and make it incentive-compatible for participants to choose the “right” variant.
Using a randomized controlled trial of incentives for exercise among 6,800 adults with
diabetes and hypertension in urban India, we show that personalizing with mechanism
design substantially improves program performance, increasing the treatment effect on
exercise by 75% without increasing program costs relative to a one-size-fits-all benchmark.
Personalizing with mechanism design also performs favorably relative to another
potential strategy for personalization: personalizing based on observables.