##### Scenario Lyft notices that ride wait times (ETA) have increased 20% month-over-month. The team suspects that static pricing may be the culprit and is considering a switch to dynamic pricing. ##### Question Work through the following three parts: 1. **Root-cause analysis.** Ride wait times have grown 20% MoM at Lyft. How would you structure an analysis to systematically identify the root causes? Define your KPIs, slice by city/zone/time, and inspect the supply–demand and matching dynamics. 2. **Cost–benefit of dynamic pricing.** Assuming pricing might be the driver, how would you assess the costs and benefits of moving from static to dynamic pricing? Quantify the trade-offs across ETA, revenue/margin, rider experience, and driver earnings. 3. **Experiment design.** How would you design an experiment to validate whether dynamic pricing actually reduces ETAs without degrading other key metrics, while controlling for demand–supply interference in a two-sided marketplace? ##### Hints Think about rider/driver funnels, KPI definition, cohort and geo/time slicing, the supply–demand ratio and its (nonlinear) relationship to wait time, demand and supply elasticities, cost–revenue simulation, and interference-robust experiment designs (switchback or geo-cluster tests).