Prediction of passenger demand using a linear regression model in R

Abstract

When managing urban public transport, it is important to know the demand for the means of transport in order to determine if it is necessary to increase the number of buses, the frequency or the routes that pass through a stop. The objective of this research is to estimate the calculation of the demand for bus stops based on the analysis of the characteristics of the area using linear regression with the support of statistical software in order to avoid the need to make manual counts that in many cases are expensive and take too long. In order to obtain the coefficients of the linear regression model, a sample of 20 bus stops in the city of Riobamba was taken, of which a manual count of boarding and alighting was carried out, as well as the characteristics of the area such as the presence of educational units of middle and higher level, commercial premises, markets, and financial institutions. With the generated model it was possible to reach a determination coefficient of 59.93%, which indicates that there is a percentage of the data that can be predicted by using the characteristics of the areas taken into account in the present study, however, the increase of characteristics of the zones can improve the results of the model.