Research Reports
Report Details
Abstract
Achieving and maintaining public transportation rolling stocks in a state of good repair is very crucial to providing safe and reliable services to riders. Transit agencies that seek federal grants must also keep their transit assets in a state of good repair. Therefore, transit agencies in small urban and rural transit systems need an intelligent predictive model for analyzing their transportation rolling stocks, determining the current conditions, predicting when they need to be replaced or rehabilitated, and determining the funding needed to replace in a future year to maintain the state of good repair. Since many transit agencies in small urban and rural transit systems do not have adequate analytical tools for predicting the service life of vehicles, this simple predictive model would be a valuable resource for their state of good repair needs and their prioritization of capital needs for replacement and rehabilitation.
The ability to accurately predict the service life of revenue vehicles is crucial in achieving the state of good repair. In this research, three unique tree-based ensemble learning methods have been applied to build three predictive models. The machine learning methods used in this research are random forest regression, gradient boosting regression, and decision tree regression. After evaluation and comparison of the performance results among all models, the gradient boosting regression model with the top 35 most important features was found to be the best fit for predicting the service life of transit vehicles. This model can be used to predict the projected retirement year for all small urban and rural vehicles in operation.