Detecting and analyzing unlicensed taxis: A case study of Chongqing City

Li Chen, Linjiang Zheng, Li Xia, Weining Liu and Dihua Sun

Physica A: Statistical Mechanics and its Applications, 2021, vol. 584, issue C

Abstract: Unlicensed taxis are private vehicles that are not duly licensed or permitted by the jurisdiction in which they operate. Trajectory data contain rich behavior features of mobile objects, which are valuable for unlicensed taxi detection. (Electronic Registration Identification) ERI of the motor vehicle is a way to collect trajectory data. ERI’s advantage is that it can record all kinds of vehicles traveling in the city, including taxis, private vehicles. As a pilot city of ERI in China, Chongqing has formed a massive ERI trajectory dataset of motor vehicles. This dataset provides us with an opportunity to detect and analyze unlicensed taxis from a data-driven aspect. In this paper, we complete two main works: detecting city-wide unlicensed taxis and analyzing them. Firstly, we build an unlicensed taxis detection model based on an ensemble learning approach, random forest(RF). The goal of ensemble learning is to improve prediction, generalizability, and robustness over a single classifier. We employ taxis and commuting private vehicles as training samples. The core idea is that unlicensed taxis and taxis are similar in many aspects. We also innovatively utilize the POI information as an input feature to the unlicensed taxi detection model. With the comparison of some baseline models, we have proved our model’s superiority on the ERI dataset. So, we apply the detection model on a real-world dataset and detect the city-wide potential unlicensed taxis. Secondly, we conduct some statistical analysis with the detected potential unlicensed taxis. We find that unlicensed taxis do behave very much like taxis. The hot areas of taxis and unlicensed taxis are not the same, which provides vital information for further traffic management.

Keywords: Unlicensed taxis; ERI data; Random forest; Machine learning; Spatial–temporal features (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378437121005975
Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:phsmap:v:584:y:2021:i:c:s0378437121005975

DOI: 10.1016/j.physa.2021.126324

Access Statistics for this article

Physica A: Statistical Mechanics and its Applications is currently edited by K. A. Dawson, J. O. Indekeu, H.E. Stanley and C. Tsallis

More articles in Physica A: Statistical Mechanics and its Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().