Abstract. This system aims to address the problem of traffic congestion that appeared to be caused by the fast and rapid urban sprawl of Metro Manila, which happened together with a failure in proper planning and increasing the number of vehicles. More advanced bracketing algorithms are developed for optimum flexible urban traffic management systems under real-time traffic flow conditions and signal timings for congestion and travel efficiency. It uses cross-sectional study designs where real-time data are collected for traffic conditions in Metro Manila and is used to develop and test proposed algorithms. The experiments reduced congestion by 25 % and improved travel time on major routes in the city by 18%. Regression analysis and machine learning algorithms-based developed predictive models will be used for predicting traffic, thereby initiating adaptive traffic signal control with optimal signal timing for improvement in bottleneck intersection traffic flow. Proposed algorithms have proven to significantly decrease traffic congestion, facilitate the use of public transport, and decrease dependence on private vehicles. The mentioned advances will thus promote economic development, environmental friendliness, and better health. The proposed research constitutes an excellent case study regarding integrating more developed bracketing algorithms in traffic management systems nowadays to address the challenges towards a more sustainable urban environment.

Keywords: Adaptive signal control; Bracketing algorithms; Predictive analytics; Traffic congestion; Traffic management.