A predictive model for the passenger demand on a taxi network (original) (raw)

Online Predictive Model for Taxi Services

Lecture Notes in Computer Science, 2012

In recent years, both companies and researchers have been exploring intelligent data analysis to increase the profitability of the taxi industry. Intelligent systems for online taxi dispatching and time saving route finding have been built to do so. In this paper, we propose a novel methodology to produce online predictions regarding the spatial distribution of passenger demand throughout taxi stand networks. We have done so by assembling two well-known time series short-term forecast models: the time-varying Poisson models and ARIMA models. Our tests were performed using data gathered over a period of 6 months and collected from 63 taxi stands within the city of Porto, Portugal. Our results demonstrate that this model is a true major contribution to the driver mobility intelligence: 78% of the 253745 demanded taxi services were correctly forecasted in a 30 minutes horizon.

On Predicting the Taxi-Passenger Demand: A Real-Time Approach

Lecture Notes in Computer Science, 2013

Informed driving is becoming a key feature to increase the sustainability of taxi companies. Some recent works are exploring the data broadcasted by each vehicle to provide live information for decision making. In this paper, we propose a method to employ a learning model based on historical GPS data in a real-time environment. Our goal is to predict the spatiotemporal distribution of the Taxi-Passenger demand in a short time horizon. We did so by using learning concepts originally proposed to a well-known online algorithm: the perceptron [1]. The results were promising: we accomplished a satisfactory performance to output the next prediction using a short amount of resources.

Taxi-Passenger-Demand Modeling Based on Big Data from a Roving Sensor Network

IEEE Transactions on Big Data, 2017

Investigating passenger demand is essential for the taxicab business. Existing solutions are typically based on offline data collected by manual investigations, which are often dated and inaccurate for real-time analysis. To address this issue, we propose Dmodel, employing roving taxicabs as real-time mobile sensors to (i) infer passenger arriving moments by interactions of vacant taxicabs, and then (ii) infer passenger demand by customized online training with both historical and real-time data. Dmodel utilizes a novel parameter called pickup pattern based on an entropy of pickup events (accounts for various real-world logical information, e.g., bad weather) to reduce the size of big historical taxicab data to be processed. We evaluate Dmodel with a real-world 450 GB dataset of 14,000 taxicabs for a half year, and results show that compared to the ground truth, Dmodel achieves 83 percent accuracy and outperforms a statistical model by 42 percent. We further present an application where Dmodel is used to dispatch vacant taxicabs to achieve an equilibrium between passenger demand and taxicab supply across urban regions.

Predicting the Upcoming Services of Vacant Taxis near Fixed Locations Using Taxi Trajectories

ISPRS International Journal of Geo-Information, 2019

Emerging on-line reservation services and special car services have greatly affected the development of the taxi industry. Surprisingly, taking a taxi is still a significant problem in many large cities. In this paper, we present an effective solution based on the Hidden Markov Model to predict the upcoming services of vacant taxis that appear at some fixed locations and at specific times. The model introduces a weighted confusion matrix and a modified Viterbi algorithm, combining the factors of time of day and traffic conditions. In our framework, the hotspot or hidden states extraction is implemented through kernel density estimation (KDE) and fuzzy partitioning of traffic zones is done via a Fuzzy C Means (FCM) algorithm. We implement the proposed model on a large-scale dataset of taxi trajectories in Beijing. In this use case, tests demonstrate the high accuracy of the modeling framework in predicting the upcoming services of vacant taxis. We further analyze the factors affectin...

SOUP: A Fleet Management System for Passenger Demand Prediction and Competitive Taxi Supply

2021 IEEE 37th International Conference on Data Engineering (ICDE)

Online car-hailing services have gained substantial popularity. An effective taxi fleet management strategy should not only increase taxi utilization by reducing taxi idle time, but should also improve passenger satisfaction by minimizing passenger waiting time. We demonstrate a fleet management system called SOUP that aims at minimizing taxi idle time and that monitors the fleet movement status. SOUP includes a passenger request prediction model called ST-GCSL that predicts the number of requests in the near future, and it includes a demand-aware route planning algorithm called DROP that provides idle taxis with search routes to serve potential requests. In addition, SOUP supports visualizing and analyzing historical passenger requests, simulating fleet movement, and computing evaluation metrics. We demonstrate how SOUP accurately predicts passenger demand and significantly reduces taxi idle time.

Dmodel: Online Taxicab Demand Model from Big Sensor Data in a Roving Sensor Network

2014 IEEE International Congress on Big Data, 2014

Investigating passenger demand is essential for the taxicab business. Existing solutions are typically based on offline data collected by manual investigations, which are often dated and inaccurate for real-time analysis. To address this issue, we propose Dmodel, employing roving taxicabs as real-time mobile sensors to (i) infer passenger arriving moments by interactions of vacant taxicabs, and then (ii) infer passenger demand by a customized online training with both historical and real-time data. Such huge taxicab data (almost 1TB per year) pose a big data challenge to us. To address this challenge, Dmodel employs a novel parameter called pickup pattern (accounts for various real world logical information, e.g., bad weather) to reduce the size of data to be processed. We evaluate Dmodel with a real world 450 GB dataset of 14, 000 taxicabs for a half year, and results show that compared to ground truth, Dmodel achieves a 76% accuracy on the demand inference and outperforms a statistical model by 39%. We further present an application where Dmodel is used to dispatch vacant taxicabs to achieve an equilibrium between passenger demand and taxicab supply across urban regions.

Taxi Demand Prediction using Machine Learning

IRJET, 2023

Taxi demand prediction is the process of using historical data to forecast future taxi requests in a particular area. Managers may pre-allocate taxi resources in cities with the aid of accurate and real-time demand forecasting, which helps drivers find clients more quickly and cuts down on passenger waiting times. This project is aimed to choose the best model in predicting the taxi demand where we use various Machine learning techniques such as regression analysis and time series forecasting. Various baseline models, including moving averages (simple, weighted, and exponential), linear regression with grid search, random forest regressor with random search, and XGBoost regressor with random search are used. We find out which model is more suitable in predicting the output using the metrics we obtain.

iTaxi: Context-Aware Taxi Demand Hotspots Prediction

It has been estimated that over 60 thousand licensed taxis in the Great Taipei area are not occupied over 70 percent of driving time on average. However, the taxi company, TaiwanTaxi, indicates that even in rush hour, there are customers whose requests are not satisfied. The demand and supply are not paired, causing not only customers wait too long for a cab, but also taxi drivers waste time and fuel to wander around the streets. In this paper, it uses spatial statistics analysis, data mining and clustering algorithm on historical data of taxi requests to discover the demand distribution, which varies from different environment contextual information such as the location, time, and weather. Finally, the predicting system then predicts potential hotspots of taxi requests and provides hotspots information for drivers to reduce vacant time of the taxi.

Estimating Taxi Demand-Supply Level Using Taxi Trajectory Data Stream

2015 IEEE International Conference on Data Mining Workshop (ICDMW), 2015

Taxis provide a flexible and indispensable service to satisfy the urban travel demand of public commuters. Understanding taxi supply and commuter demand, especially the imbalance between the supply and the demand, would directly help to improve the quality of taxi service and eventually increase a city's traffic system efficiency. In this paper, we consider the taxi demand from a region during a period of time to include two parts: satisfied demand, i.e., passengers successfully receive taxi service during this period of time, and unmet demand, i.e., passengers are still waiting for taxi service. To properly estimate the demand-supply level (short for "the level of the taxi demand vs. supply imbalance"), we propose a novel indicator that reflects how fast an available taxi is taken in any given region. Accordingly, we design and implement a taxi analytics system to provide such information in near real time. Finally, we use the passenger waiting time survey data and the taxi streaming data to validate the proposed indicator on the built taxi analytics system.

Real time location prediction with taxi-GPS data streams

Transportation Research Part C-emerging Technologies, 2018

The prediction of the destination location at the time of pickup is an important problem with potential for substantial impact on the efficiency of a GPS enabled taxi service. While this problem has been explored earlier in the batch data setup , we propose in this paper new solutions in the streaming data setup. We examine four incremental learning methods using a Damped window model namely, Multivariate multiple regression, Spherical-spherical regression, Randomized spherical K-NN regression and an Ensemble of these methods for their effectiveness in solving the destination prediction problem. The performance of these methods on several large datasets are evaluated using suitably chosen metrics and they were also compared with some other existing methods. The Multivariate multiple regression method and the Ensemble of the three methods are found to be the two best performers. The next pickup location problem is also considered and the aforementioned methods are examined for their suitability using real world datasets. As in the case of destination prediction problem, here also we find that the Multivariate multiple regression method and the Ensemble of the three methods gives better performance than the rest.