Joint Optimization of Bus Scheduling and Targeted Bus Exterior Advertising

Abstract

Bus exterior advertising provides a powerful way to establish brand awareness since it can reach a mass of audiences with a high frequency. For a certain advertisement category, the advertising effectiveness is largely depended upon its exposure times to the target audience who takes interests of the advertisement, which is termed as targeted advertising. Given that the distribution of target audiences over a city varies among different advertisement categories, a practical way of enhancing overall advertising effectiveness is to deploy the bus with certain advertisement category to the bus line that best fits it "target area". This gives rise to a decision-making problem of targeted bus exterior advertising and bus scheduling. In this paper, the problem is formulated as a bi-objective optimization model with objectives of maximizing the quantified advertising effectiveness and minimizing the number of bus fleet size to cover all trips. The advertising effectiveness is quantified using the audience demographic data. The deadheading of buses is also enabled in the scheduling process to facilitate both objectives. The NSGA-II-LNS algorithm is developed to solve the bi-objective problem with the incorporation of large neighborhood search operators into the framework of the NSGA-II to improve This material may be downloaded for personal use only. Any other use requires prior permission of the American Society of Civil Engineers. This material may be found at https://ascelibrary.org/doi/10.1061/JTEPBS.TEENG-7812. This is the Pre-Published Version. 2 solution quality. Various experiments are set up to verify the proposed model and solution algorithm.