Learning Individual Behavior Using Sensor Data: The Case of Global Positioning System Traces and Taxi Drivers

Zhang, Yingjie; Li, Beibei; Krishnan, Ramayya

doi:10.1287/isre.2020.0946

Cited by 29 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the field of economics, the literature on the taxi industry mainly focuses on the labor supply issue, particularly on how taxi drivers decide their hours of work and where they drive to look for passengers (Camerer et al., 1997; Farber, 2005; Fréchette et al., 2019; Zhang et al., 2020). A small number of economics papers have examined taxi drivers’ routing decisions (e.g., which route to choose among hundreds of potential ones) in the context of information asymmetry.…”

Section: Literature and Theoretical Foundationsmentioning

confidence: 99%

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

Lu,

Wang,

Chen

et al. 2023

Production and Operations Management

View full text Add to dashboard Cite

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 apps with embedded GPS system, and 2) a measure of Non‐Recurring Congestion (NRC) 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.This article is protected by copyright. All rights reserved

show abstract

Section: Literature and Theoretical Foundationsmentioning

confidence: 99%

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

Lu,

Wang,

Chen

et al. 2023

Production and Operations Management

View full text Add to dashboard Cite

show abstract

“…[59] study participants' learning behavior from superstars in crowdsourcing contests. [60] examine taxi drivers' learning behavior based on fine-grained GPS observations. In this paper, we model the learning dynamics in loan application evaluators' decisions, and disentangle and estimate preference-based bias and belief-based bias in their behavior.…”

Section: Relevant Literaturementioning

confidence: 99%

Uncovering the Source of Machine Bias

Hu¹,

Huang²,

Li³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

We develop a structural econometric model to capture the decision dynamics of human evaluators on an online micro-lending platform, and estimate the model parameters using a real-world dataset. We find two types of biases in gender, i.e. preference-based bias and belief-based bias, are present in human evaluators' decisions. Both types of biases are in favor of female applicants. Through counterfactual simulations, we quantify the effect of gender bias on loan granting outcomes and the welfare of the company and the borrowers. Our results imply that both the existence of the preference-based bias and that of the belief-based bias reduce the company's profits. When the preference-based bias is removed, the company earns more profits. When the belief-based bias is removed, the company's profits also increase. Both increases result from raising the approval probability for borrowers, especially male borrowers, who eventually pay back loans. For borrowers, the elimination of either bias decreases the gender gap of the true positive rates in the credit risk evaluation. We also train machine learning algorithms on both the real-world data and the data from the counterfactual simulations. We compare the decisions made by those algorithms to see how evaluators' biases are inherited by the algorithms and reflected in machine-based decisions. We find that machine learning algorithms can mitigate both the preferencebased bias and the belief-based bias. CCS CONCEPTS• Computing methodologies → Machine learning.

show abstract

“…Driver experience and learning is a less studied topic. Besides [13] and [29], [35] showed that neighborhood-specific local experience has a significant impact on drivers' search strategies following drop-offs; and [36] showed that highincome drivers benefit significantly from their ability to learn from local and global demand information.…”

Section: Introductionmentioning

confidence: 99%

Drivers learn city-scale dynamic equilibrium

Zhang

Ghanem

2021

Preprint

View full text Add to dashboard Cite

Understanding driver behavior in on-demand mobility services is crucial for designing efficient and sustainable transport models. Drivers' delivery strategy is well understood, but their search strategy and learning process still lack an empirically validated model. Here we provide a game-theoretic model of driver search strategy and learning dynamics, interpret the collective outcome in a thermodynamic framework, and verify its various implications empirically. We capture driver search strategies in a multi-market oligopoly model, which has a unique Nash equilibrium and is globally asymptotically stable. The equilibrium can therefore be obtained via heuristic learning rules where drivers pursue the incentive gradient or simply imitate others. To help understand city-scale phenomena, we offer a macroscopic view with the laws of thermodynamics. With 870 million trips of over 50k drivers in New York City, we show that the equilibrium well explains the spatiotemporal patterns of driver search behavior, and estimate an empirical constitutive relation. We find that new drivers learn the equilibrium within a year, and those who stay longer learn better. The collective response to new competition is also as predicted. Among empirical studies of driver strategy in on-demand services, our work examines the longest period, the most trips, and is the largest for taxi industry.

show abstract

Learning Individual Behavior Using Sensor Data: The Case of Global Positioning System Traces and Taxi Drivers

Cited by 29 publications

References 39 publications

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

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

Uncovering the Source of Machine Bias

Drivers learn city-scale dynamic equilibrium

Contact Info

Product

Resources

About