Experimentally evaluate jogging-route recommendations

Google Maps plans to recommend optimal jogging routes. Design the evaluation: pick a single primary metric (e.g., jog completion rate) and define secondary metrics (route adherence, repeat jog within 7 days, safety incidents, time variance vs baseline route, battery drain); specify eligibility and triggering logic—expose only when the user has opted into fitness mode, location accuracy <30m, speed 1–4 m/s, and a route suggestion is shown; define experimental unit and assignment, prevent contamination (multiple devices, social sharing), and list guardrails (crash rate, navigation reroutes, ETA accuracy); compute MDE and sample size for a baseline completion rate of 40% with an expected +3pp lift, 80% power, α=0.05, stating formulas and any clustering/novelty adjustments; propose a ramp plan, geographic stratification, novelty decay checks, and a rollback criterion.