Modeling of COVID-19's impact on employee's travel behavior

Millions of people all over the world have affected their lifestyles due to the COVID-19 pandemic. The nearly three-month closure in India, followed by a return to normalcy, has had a significant impact on the transportation sector. Because working people are the most affected by the epidemic, the present study focuses on employee travel behavior, which is critical for transportation planning. To develop transportation policies for the post-COVID-19 era, it is important to investigate how the epidemic changed travel behavior patterns. Using a questionnaire survey, this study examined the impact of the COVID-19 epidemic on employee travel patterns. From the results, it is observed that gender, two-wheeler ownership, travel time, and travel distance were significant characteristics of travel behavior before COVID-19 whereas age, educational qualification, employment status, travel time, and travel distance were significant characteristics of travel behavior after lifting COVID-19 restrictions. During the lockdown, the number of trips decreased because most organizations allow employees to work from home whereas the number of trips for medical services increased due to fear of the pandemic. Multiple Linear Regression (MLR) and Artificial Neural Networks (ANN) models were developed to understand the changes in travel behavior before and after the epidemic. Validation of mathematical models was done based on Receiver operating characteristic (ROC) curves and Area under curve (AUC) values. The study's findings will help in the formulation of transportation planning and policies for the post-COVID-19 era, particularly in developing countries. The outcomes could help transportation providers better plan their services and operations.