Characterizing the Importance of Criminal Factors Affecting Bus Ridership using Random Forest Ensemble Algorithm

Abstract

Public transit systems provide mass movement with substantial traffic operational and environmental benefits. Despite these benefits, they still represent a small market share in the United States. A comprehensive understanding of the determinants of transit ridership is essential for investment allocation to improve safety, mobility, and air quality in an urban area. Except socio-economic factors, crime has been identified as a determinant for the ridership. Most studies found that ridership and crime are linearly correlated to each other, whereas other studies believed the level of crime can result in a nonlinear effect on the ridership. The relationship between ridership and crime remains inconclusive. Besides, the simultaneous relationship between ridership and crime is scarcely addressed and most ridership studies only include one or a few external factors that affect crime opportunity. This paper proposes a random-forest-based feature selection method to characterize the importance of multiple variables, to bus ridership and total crime, respectively, at different levels. A case study in Houston, Texas, USA, for the year 2017 is provided to illustrate the feature selection and modeling process. A total of 110,885 crimes, ridership on 9004 bus stops, and related socio-economic information were collected. Results indicated that a medium or lower level of ridership is positively correlated to crime; the linear relationship can be broken down at a high level; and reducing the total crime per capita can promote bus ridership. Random-forest-based models were developed with the selected determinants, performing with high accuracy in ridership per capita estimates.

Estratificación Social Y Uso Del Transporte Público en El Contexto De La Crisis De Seguridad en México

“…Investigaciones posteriores en este mismo país han revelado que existe un umbral en donde el delito y la percepción de la inseguridad comienzan a hacerse determinantes en esta explicación del uso del transporte. Li et al (2019) mostraron que solo en ciudades y países con elevados niveles de delitos, la inseguridad se convierte en significativa para explicar los comportamientos de viaje. Este sería el caso de países del Sur Global como México y Nigeria, donde la extensión de la violencia implica la reducción de usuarios del transporte público (Vilalta, 2011;Odufawa, 2012).…”

Fuzzy Neural Network for Studying Coupling between Drilling Parameters

“…Random forest is an integrated learning algorithm. , It has good tolerance for outliers and strong robustness. Its principle is to extract parts of the samples repeatedly from the sample set to generate multiple decision trees.…”

Public Transportation Operational Health Assessment Based on Multi-Source Data

“…Among commonly used supervised learning machine learning algorithms, the SVM (Data Envelopment Analysis) algorithm is generally suitable for binary classification problems [23,24], and the Naive Bayes algorithm is suitable for datasets with mutually independent feature values [25]. The Decision Tree algorithm [26,27], the K-Nearest Neighbors algorithm [28], and the Random Forest algorithm [29,30] are all more effective methods for the dataset under study. The K-Nearest Neighbors is easy to understand, simple and effective, relatively insensitive to outliers, and capable of solving both binary classification and multi-classification problems.…”