Big Data Analytics: Estimation of Destination for Users of Bus Rapid Transit (BRT) Public Transportation in Jakarta

Abstract

Origin-Destination (OD) matrix is a metric which has become the main requirement in the analysis of the transportation system. This measurement has been made a model for management, development, and transportation planning purposes. Entering the era of big data, the infrastructure that is used to measure OD matrices has also changed. Due to the development of the Intelligence Transportation System (ITS), estimation of the origin-destination flow of transportation users is utilized as an approach to observe travel behavior of public transport users formulated in the OD matrix. The infrastructure has been developed a lot to get user's behavior by recording their transactions. This research presents the method of alighting station estimation from the Automated Fare Collection (AFC) transaction data on Bus Rapid Transit (BRT) smart card users between bus stations and corridors, with OD matrices as its parameters. The estimated travel destination of users with the same day trip chaining approach was explained in this study. Validation is done by comparing OD matrices with available entry-exit AFC. The comparison of the results of estimated validation between corridors and stops as a comparison of the scope of research on the behavior of travel users is presented. The purpose of this study is to determine the level of validity of the OD matrix estimation results validated with AFC data entries using the method approach that had been offered. The results of comparisons at each level (corridor - bus stop) show that the approach provides results with accuracy up to 94%. The comparison of destination estimation at each level shows that OD matrix validity will be better at higher levels.