Taxi Trips Research Articles

Flow Cross K-function: a bivariate flow analytical method

ABSTRACTSpatial flow data represent meaningful interaction activities between pairs of corresponding locations, such as daily commuting, animal migration, and merchandise shipping. Despite recent advances in flow data analytics, there is a lack of literature on detecting bivariate or multivariate spatial flow patterns. In this paper we introduce a new spatial statistical method called Flow Cross K-function, which combines the Cross K-function that detects marked point patterns and the Flow K-function that detects univariate flow clustering patterns. Flow Cross K-function specifically assesses spatial dependence of two types of flow events, in other words, whether one type of flows is spatially associated with the other, and if so, whether this is according to a clustering or dispersion trend. Both a global version and a local version of Flow Cross K-function are developed. The former measures the overall bivariate flow patterns in the study area, while the latter can identify anomalies at local scales that may not follow the global trend. We test our method with carefully designed synthetic data that simulate the extreme situations. We exemplify the usefulness of this method with an empirical study that examines the distributions of taxi trip flows in New York City.

GPS data in urban online ride-hailing: A comparative analysis on fuel consumption and emissions

Abstract: The transportation sector has become the leading and most-rapidly growing contributor to greenhouse gas emissions. Promoting low-carbon travel mode is critical to alleviate this issue. As a new travel mode, online ride-hailing (such as Didi Chuxing and Uber), is becoming increasingly popular in cities around the world. However, there is still no comparative analysis on fuel consumption and emissions: does online ride-hailing have a distinct fuel consumption and emissions pattern with traditional taxis? In this study, we use one month global positioning system dataset and orders dataset, averagely covering around 7 thousand taxis with 0.3 million trips and 23 thousand Didi Chuxing Express vehicles with 0.1 million trips per day in Chengdu, China to answer this question. Empirical results show that taxi trips associate with longer idle distance and shorter delivery distance than Didi trips. Didi trips’ average idle velocity is apparently smaller than their delivery velocity. Online ride-hailing mode is concluded to contribute to these difference: after dropping off previous passengers, Didi drivers usually park their cars until being dispatched new orders and then drive directly to pick up passengers rather than search circuitously. Fuel consumption and carbon monoxide, nitrogen oxides, hydrocarbon emissions per passenger-on kilometer of taxi trips are found to be about 1.36, 1.45, 1.36 and 1.44 times that of Didi trips, respectively. Additionally, only taxi drivers with good performance have the ability to reduce fuel consumption and emissions; while most Didi drivers can perform well on fuel consumption saving and emissions reduction. Finally, several feasible policies are suggested for improving and upgrading the traditional taxi business. Our study provides convincing evidence for understanding the advantage of online ride-hailing mode in reduction fuel consumption and emissions sourced from empty cruising, so as to support better traffic policy making and the promotion on low-carbon travel mode.

Analyzing Spatio-Temporal Distribution Pattern and Correlation for Taxi and Metro Ridership in Shanghai

Taxicab is an important mode in urban transportation system, while the role of taxicabs, especially the relationship with metro system has not been fully studied. This study aims at exploring the factors influencing the role played by taxicabs in Shanghai, China. Firstly, taxi trips are categorized into three types, namely metroreplaceable (MR), metro-extending (ME) and metro-supplement (MS) ones. Then, the tendency of travelers towards taxi or metro at a specific metro station is proposed and calculated on the basis of MR taxi trips and metro trips. Factors influencing the tendency are investigated through semi-parametric regression models, with the results indicating that the most significant factors and the influencing radii during the peak and off-peak hours are different. Some built environment factors, such as the number of hospitals and government agencies, have significant positive relationship with the tendency in the time periods. Furthermore, land use related factors, such as the increase of forestry and commercial land, generally promote taxi-hiring in the off-peak hours, while they have a negative impact during the peak hours. Findings of this study can assist governments and policy makers to understand the impact of built environment and land use on trip patterns, and thus may contribute to more reasonable policies and optimized urban planning, which may promote modal switch from taxi to subway.

DeepPool: Distributed Model-Free Algorithm for Ride-Sharing Using Deep Reinforcement Learning

The success of modern ride-sharing platforms crucially depends on the profit of the ride-sharing fleet operating companies, and how efficiently the resources are managed. Further, ride-sharing allows sharing costs and, hence, reduces the congestion and emission by making better use of vehicle capacities. In this work, we develop a distributed model-free, DeepPool, that uses deep Q-network (DQN) techniques to learn optimal dispatch policies by interacting with the environment. Further, DeepPool efficiently incorporates travel demand statistics and deep learning models to manage dispatching vehicles for improved ride sharing services. Using real-world dataset of taxi trip records in New York City, DeepPool performs better than other strategies, proposed in the literature, that do not consider ride sharing or do not dispatch the vehicles to regions where the future demand is anticipated. Finally, DeepPool can adapt rapidly to dynamic environments since it is implemented in a distributed manner in which each vehicle solves its own DQN individually without coordination.

Extracting Interesting Regions and Trips from Taxi Trajectory Data

The increasing availability of cutting-edge location-acquisition technologies such as GPS devices, has led to the generation of huge datasets of spatial trajectories. These trajectories store important information regarding the movement of people, vehicles, robots, animals, users of social networks, etc. Many research initiatives have applied data mining techniques in order to extract useful knowledge from this data.  An important, and yet complicated, pre-processing step in mining patterns from trajectory data, is the identification of the Regions of Interest (RoI) that have been collectively navigated by a set of trajectories. The RoI’s are being manually and subjectively pre-defined by a group of experts as popular regions, regardless of the actual behaviour of the moving objects. This research emphasizes the usefulness of applying an unsupervised machine learning technique, namely Self Organizing Map (SOM), in order to identify the RoI’s associated with a trajectory dataset depending on the moving objects’ behaviour. The research experiments were conducted using 180 thousand of the trajectories generated by 442 taxis running in the city of Porto, in Portugal, and they demonstrate the ability of SOM in identifying the RoI’s and interesting taxi trips within the city.

Temporal patterns of driving fatigue and driving performance among male taxi drivers in Hong Kong: A driving simulator approach

This study uses a questionnaire survey and a driving simulator test to investigate the temporal patterns of variations in driving fatigue and driving performance in 50 male taxi drivers in Hong Kong. Each driver visited the laboratory three times: before, during, and after a working shift. The survey contained a demographic questionnaire and the Brief Fatigue Inventory. A following-braking simulator test session was conducted at two speeds (50 and 80 km/h) by each driver at each of his three visits, and the driver’s performance in brake reaction, lane control, speed control, and steering control were recorded. A random-effects modeling approach was incorporated to address the unobserved heterogeneity caused by the repeated measures. In the results, a recovery effect and a lagging effect were defined for the driving fatigue and performance measures because their temporal patterns were concavely quadratic and had a 1-hour delay compared to the temporal patterns of occupied taxi trips and taxi crash risk in Hong Kong. Demographic variables, such as net income and driver age, also had significant effects on the measured driving fatigue and performance. Policies regarding taxi management and operation based on the modeling results are proposed to alleviate the taxi safety situation in Hong Kong and worldwide.

A Simple Baseline for Travel Time Estimation using Large-scale Trip Data

The increased availability of large-scale trajectory data provides rich information for the study of urban dynamics. For example, New York City Taxi 8 Limousine Commission regularly releases source/destination information of taxi trips, where 173 million taxi trips released for Year 2013 [29]. Such a big dataset provides us potential new perspectives to address the traditional traffic problems. In this article, we study the travel time estimation problem. Instead of following the traditional route-based travel time estimation, we propose to simply use a large amount of taxi trips without using the intermediate trajectory points to estimate the travel time between source and destination. Our experiments show very promising results. The proposed big-data-driven approach significantly outperforms both state-of-the-art route-based method and online map services. Our study indicates that novel simple approaches could be empowered by big data and these approaches could serve as new baselines for some traditional computational problems.

Spatiotemporal Influence of Urban Environment on Taxi Ridership Using Geographically and Temporally Weighted Regression

Taxicabs play an important role in urban transit systems, and their ridership is significantly influenced by the urban built environment. The intricate relationship between taxi ridership and the urban environment has been explored using either conventional ordinary least squares (OLS) regression or geographically weighted regression (GWR). However, time constitutes a significant dimension, particularly when analyzing spatiotemporal hourly taxi ridership, which is not effectively incorporated into conventional models. In this study, the geographically and temporally weighted regression (GTWR) model was applied to model the spatiotemporal heterogeneity of hourly taxi ridership, and visualize the spatial and temporal coefficient variations. To test the performance of the GTWR model, an empirical study was implemented for Xiamen city in China using a set of weekday taxi pickup point data. Using point-of-interest (POI) data, hourly taxi ridership was analyzed by incorporating it to various spatially urban environment variables based on a 500 × 500 m grid unit. Compared to the OLS and GWR, the GTWR model obtained the best performance, both in terms of model fit and explanatory accuracy. Moreover, the urban environment was revealed to have a significant impact on taxi ridership. Road density was found to decrease the number of taxi trips in particular places, and the density of bus stops competed with taxi ridership over time. The GTWR modelling provides valuable insights for investigating taxi ridership variation as a function of spatiotemporal urban environment variables, thereby facilitating an optimal allocation of taxi resources and transportation planning.

Visualizing spatial interaction characteristics with direction-based pattern maps

In the era of big data, large amounts of detailed spatial interaction data are readily available due to the increasing pervasiveness of location-aware devices and techniques. Such data are often applied in the research of spatial structures, land use characteristics, and human activity regularities. However, visualizing such data on maps is a great challenge. Existing approaches either encounter overlapping and intersection problems, which may cause information loss or distortion, or are unable to present interaction characteristics. Consequently, the functional and positional features of places and human mobility trends are not fully demonstrated. We propose direction-based pattern maps, a new visualization method to display the spatial interaction pattern of every place by aggregating spatial interaction data in cardinal directions. This approach can well represent local interaction characteristics and is applicable to different spatial scales. Owing to regular hexagonal tessellations, it can avoid cluttering problems and maintain a geographical context. A case study using Beijing taxi trip data is conducted to validate the usefulness of our approach.

Big Data Analytics of Taxi Operations in New York City

As a global financial center, the transportation system in New York City (NYC) has always been studied from various aspects. Since 2009, NYC Taxi and Limousine Commission have made public the information on NYC taxi operations, offering an opportunity for detailed analysis. Thus, this research project investigates taxi operations in New York City based on big data analysis. The correlation between taxi operations and different types of weather, including precipitation, snow depth, and snowfall is discussed in this paper. The research also evaluates taxi trip distribution in each NTA area using Geopandas, and presents its density on an NYC map.

Data-Driven Robust Taxi Dispatch Under Demand Uncertainties

In modern taxi networks, large amounts of taxi occupancy status and location data are collected from networked in-vehicle sensors in realtime. They provide knowledge of system models on passenger demand and mobility patterns for efficient taxi dispatch and coordination strategies. Such approaches face new challenges: how to deal with uncertainties of predicted customer demand while fulfilling the system’s performance requirements, including minimizing taxis’ total idle mileage and maintaining service fairness across the whole city; how to formulate a computationally tractable problem. To address this problem, we develop a data-driven robust taxi dispatch framework to consider spatial-temporally correlated demand uncertainties. The robust vehicle dispatch problem we formulate is concave in the uncertain demand and convex in the decision variables. Uncertainty sets of random demand vectors are constructed from data based on theories in hypothesis testing, and provide a desired probabilistic guarantee level for the performance of robust taxi dispatch solutions. We prove equivalent computationally tractable forms of the robust dispatch problem using the minimax theorem and strong duality. Evaluations on four years of taxi trip data for New York City show that by selecting a probabilistic guarantee level at 75%, the average demand–supply ratio error is reduced by 31.7%, and the average total idle driving distance is reduced by 10.13% or about 20 million miles annually, compared with nonrobust dispatch solutions.

ProbDetect: A choice probability-based taxi trip anomaly detection model considering traffic variability

Taxi service is an essential complement to public transport systems due to its convenience and availability. It often provides hundreds of millions of rides for urban travelers every year in cities across the world. At the same time, the number of trip-induced passenger complaints about trip anomalies (trips with anomalous trip length, time, fare, etc.) is also considerable. Hence, the taxi regulators impose harsh penalties on verified trip anomalies. The existing anomaly verification process is labor-intensive, and it does not consider the traffic variability as well as the passengers’ perception of trip anomalies. Quite often the imprecise and unfair outputs are generated as a result. To tackle this issue, we propose a choice probability-based taxi trip anomaly detection model (ProbDetect) that considers the taxi drivers’ route choice behavior as well as the traffic variability. We first generate a route choice set for each OD pair based on the massive taxi GPS trajectory data. Second, we assign each route with a choice probability derived from a cumulative multivariate probability over differences of generalized costs. Third, we distinguish the unintentional anomalies from the intentional anomalies using the expected and the realized choice probability. Lastly, the model is tested on 5000 OD pairs using 180 days of taxi GPS data in Shanghai, China. Three types of anomalies are detected as a result. Insights into the driver’s route choice behavior are derived as well.

Measuring changes in taxi trips near infill development and issues for curbside management of for-hire vehicles

This research examines changes in taxi trip origins and destinations after new multifamily residential buildings opened in New York City. We argue that taxi trips are a reasonable proxy for other for-hire vehicles trips, which are expected to grow in coming years. The analysis contributes to a more nuanced understanding of transportation effects of infill development. Infill developments are typically required to mitigate potential vehicular traffic increases, which are often ill suited to redevelopment of denser, more transit adjacent sites. This research uses geolocated trip data from New York City taxicabs combined with US Census, real estate pricing and tax lot data to develop a baseline understanding of the relationship between trip generation and infill residential development. The objective of this work is twofold. First, establish a measure of taxi activities based on neighborhood and building characteristics to help adapt transportation impact assessments for multimodal travel. Second, through observational data we discuss unique aspects of passenger pick-ups and drop offs as they relate to curb space and street use. Our results show that taxi trip making is positively associated with new residential construction, rental costs and places with high levels of transit usage, and adds demand to congested curb space. Curb space should be considered “wetlands” of urban systems, a poorly understood, yet key, component that connects the flows of traffic and activities in the built environment.

Characterization of Taxi Fleet Operational Networks and Vehicle Efficiency: Chicago Case Study

Taxi fleets serve a significant and important subset of travel demand in major cities around the world. This paper characterizes the Chicago taxi fleet operational network using complex network metrics and analyzes the operational efficiency of individual taxis over the past four years using an extensive taxi-trip dataset. The dataset, recently released by the city of Chicago, includes the pickup and drop-off census tracts and time stamps for over 100 million taxi trips. The paper explores year-over-year changes in the spatial distribution of Chicago taxi travel demand. The taxi pickup and drop-off census tract locations are modeled as nodes, and links are generated between unique pickup and drop-off node pairs. The analysis shows that high-demand pickup and drop-off location pairs in 2013 generated similar trip volumes in 2016; however, the low-demand pairs in 2013 generated significantly fewer trips in 2016. Additionally, this paper presents temporal efficiency and spatial efficiency metrics. The temporal efficiency metric determines the percentage of in-service time taxis are productive (i.e., transporting travelers), rather than empty. The spatial efficiency metric measures the percentage of taxi miles that are productive (i.e., loaded), rather than empty. The efficiency analysis of the Chicago taxi fleet shows that, for most taxis, around 50% of their in-service time and travel distance are unproductive. This inefficiency negatively affects the profitability of individual drivers and the fleet, traffic congestion, vehicle emissions, the service quality provided to customers, and the ability of taxi services to compete with emerging mobility services.

Potential of Taxi-Pooling to Reduce Vehicle Miles Traveled in Washington, D.C.

This paper presents a pilot study of taxi-pooling in Washington, D.C. to demonstrate its potential for city-wide vehicle mileage reduction with real-world taxi trip data. In the taxi-pooling problem, riders specify their origins, destinations, earliest departure times, and latest arrival times. Taking all requests into consideration, the system dispatcher determines which requests can be grouped and thus served by one taxi, without violating any user-specified time windows and taxi capacity. This paper first presents a mathematical programming model whose objective is to minimize the system-wide vehicle miles traveled. Then an efficient solution approach to this problem is proposed. Results from analyzing the case of Washington, D.C. show that the total vehicle miles traveled can be reduced by 18% if the average buffer time in their travel schedule is 25% of their direct travel time.

Discovering Fine-Grained Spatial Pattern From Taxi Trips: Where Point Process Meets Matrix Decomposition and Factorization

As increasing volumes of urban data are being available, new opportunities arise for data-driven analysis that can lead to improvements in the lives of citizens through evidence-based policies. In particular, taxi trip is an important urban sensor that provides unprecedented insights into many aspects of a city, from economic activity, human mobility to land development. However, analyzing these data presents many challenges, e.g. , sparse data for fine-grained patterns, and the regularity submerged by seemingly random data. Inspired by above challenges, we focus on Pick-Up (PU)/Drop-Off (DO) points from taxi trips, and propose a fine-grained approach to unveil a set of low spatio-temporal patterns from the regularity-discovered intensity. The proposed method is conceptually simple yet efficient, by leveraging point process to handle sparsity of points, and by decomposing point intensities into the low-rank regularity and the factorized basis patterns, our approach enables domain experts to discover patterns that are previously unattainable for them, from a case study motivated by traffic engineers.

TripImputor: Real-Time Imputing Taxi Trip Purpose Leveraging Multi-Sourced Urban Data

Travel behavior understanding is a long-standing and critically important topic in the area of smart cities. Big volumes of various GPS-based travel data can be easily collected, among which the taxi GPS trajectory data is a typical example. However, in GPS trajectory data, there is usually little information on travelers’ activities, thereby they can only support limited applications. Quite a few studies have been focused on enriching the semantic meaning for raw data, such as travel mode/purpose inferring. Unfortunately, trip purpose imputation receives relatively less attention and requires no real-time response. To narrow the gap, we propose a probabilistic two-phase framework named TripImputor , for making the real-time taxi trip purpose imputation and recommending services to passengers at their dropoff points. Specifically, in the first phase, we propose a two-stage clustering algorithm to identify candidate activity areas (CAAs) in the urban space. Then, we extract fine-granularity spatial and temporal patterns of human behaviors inside the CAAs from foursquare check-in data to approximate the priori probability for each activity, and compute the posterior probabilities (i.e., infer the trip purposes) using Bayes’ theorem. In the second phase, we take a sophisticated procedure that clusters historical dropoff points and matches the dropoff clusters and CAAs to immerse the real-time response. Finally, we evaluate the effectiveness and efficiency of the proposed two-phase framework using real-world data sets, which consist of road network, check-in data generated by over 38 000 users in one year, and the large-scale taxi trip data generated by over 19 000 taxis in a month in Manhattan, New York City, USA. Experimental results demonstrate that the system is able to infer the trip purpose accurately, and can provide recommendation results to passengers within 1.6 s in Manhattan on average, just using a single normal PC.

The analysis of urban taxi carpooling impact from taxi GPS data

Taxi is an important part of urban passenger transportation system. The research and analysis of taxi trip behavior is the key to meet the demand of urban passenger transport and solve the traffic congestion problem. Based on the GPS data of taxis in Nanjing, the statistical method is used to analyze the taxi characteristics of the average number of passengers, the average passenger time, the no-load distance and the passenger distance. By using the double logarithmic coordinate, the trip distance and trip time of taxi passengers are analyzed, it is found that the average trip distance of taxi passengers is mainly concentrated in 3-20km, and the average trip time of taxi passengers is mainly concentrated in 10-30 minutes. Using the information entropy theory to construct the equilibrium model of taxi passenger-carrying point, and analyze the spatial distribution of taxi, it is found that the distribution of urban taxi is unbalanced. The peak clustering algorithm is used to determine the location of passenger gathering points, and the hot spot of taxi trip is analyzed, it is found that the hot spots of taxi trip are mainly concentrated in the central city of Nanjing. Combined with the results of urban taxi trip analysis, from the perspective of taxi and passenger, we found that the number of urban taxis, the passenger carrying rate of taxis, the duration period of passenger trip, the duration and distance of passenger trip and the location of passenger trip points will have an impact on the urban taxi carpooling in Nanjing. By using the probability model of urban taxi carpooling, this paper discusses and analyzes the influence of these factors on urban taxi carpooling. The research in this paper can provide a reference for the effective implementation of urban taxi carpooling policy.

Shared-use mobility competition: a trip-level analysis of taxi, bikeshare, and transit mode choice in Washington, DC

ABSTRACTThe emergence of new shared-use mobility options such as bikeshare and ride-hailing services render the traditional dichotomy between personal vehicles and public transit somewhat irrelevant. Transportation planners and policymakers have yet to conclude whether these mobility technologies are complementing or competing against existing public transit services. The understanding of this relationship is vital given the increasing uncertainty of funding sources for transit services, but limited by the scarcity of meaningful data provided by the private ride-hailing industry. This study applies big data analytic tools on a unique travel data set to uncover the predictors motivating a half-billion transit, taxi, and bikeshare trips in rail station walksheds across Washington, DC. Study findings indicate travel cost and natural environment factors as well as land use diversity and network connectivity metrics significantly impact the likelihood for an individual to travel via taxi or bikeshare rather than rail.

Urban taxi ridership analysis in the emerging metropolis: Case study in Shanghai

Taxicab is one of the critical components of the urban mobility in most metropolitan areas on the world, especially in the emerging countries. Last year in Shanghai, the total 50,000 taxicabs carry 2.8 million passengers and travel 17.1 million kilometers every day. The tremendous amount of the stochastic and independent trips across the city makes the taxi problem more complex than transit such as bus and metro. Multi-source data over space and time provide an efficient way to explore the taxi ridership and travel pattern. In this study, we first summarize the historical operation records of Shanghai taxicabs, and then compare the temporal and spatial variation patterns of the taxi trips in Shanghai and New York City using GPS data. A regression model is developed to investigate the relationship between ridership and variables including urban land use, resident population, employment and car ownership. The results of this study may first improve the transportation model, and also benefit the efficiency of taxi operation and policy making.