Fickle Fingers: Ride-Hail Surge Factors and Taxi Bookings
42 Pages Posted: 25 Apr 2018 Last revised: 5 Apr 2019
Date Written: March 26, 2019
Exploiting unique features of the Singapore taxi and ride-hailing markets, we study whether consumers switch between taxis and ride-hailing based on their relative prices. We find that a 10% increase in the ride-hailing Surge Factor raises taxi bookings by 4% in the same origin area and half-hour time interval. Using random forest models, we also show that this cross-elasticity of substitution affects demand predictions: including Surge Factor information improves the out-of-sample accuracy of taxi bookings by about 15%. Our model simulation from a taxi fleet operator's perspective suggests that the improvement of the taxi booking demand prediction translates to about 9.5% reduction in vacant driver time.
Keywords: transportation economics, surge pricing, consumer behavior, big data analytics
JEL Classification: C53, D12, D47, R41
Suggested Citation: Suggested Citation