An Initial Survey Analysis on Bus Ticketing Dataset

Abstract

This research delves into the development of a prediction model for bus ticket pricing and seats available using machine-learning techniques. By leveraging a dataset comprising temporal and operational features, this research evaluates the efficacy of linear regression and random-forest models. Experimental findings reveal that the random-forest model demonstrates superior performance in predicting ticket prices and seat availability compared to linear regression. The observations extracted from this research aims to aid transportation providers and urban planners in optimizing resources and enhancing passenger satisfaction.