The role of data-based intelligence and experience on time efficiency of taxi drivers: An empirical investigation using large-scale sensor data

In this paper, we employ large-scale sensor data to examine the impact of data-based intelligence and work-related experience on the time efficiency of individual taxi drivers, measured by their propensity of choosing the fastest routes. The identification strategy is built on (1) a unique exogenous policy shock-banning taxi-hailing app with an embedded GPS system, and (2) a measure of nonrecurring congestion avoidance, enabled by the real-time sensor data, which serves as a proxy for GPS usage. Our empirical model provides evidence that data-based intelligence improves taxi drivers' routing decisions by close to 3% as measured by trip speed. Our results further demonstrate that inexperienced drivers have a higher chance of choosing the fastest route, as they are more likely to rely on the real-time traffic information from GPS technology than experienced drivers. The general implications of our findings on the adoption and utilization of data-based performance-enhancing technology are discussed in closing.