00000nam a22000003a 4500 UP-8027390931316685625 Buklod 20260221134203.0 m |o d | cr ||||||||||| 260221s2025 xx r |||| u|eng d UPVT-00020035976 UPTC rda eng LG 993.5 2025 A3 E45 Elgera, Lean Jane Letrodo author. Development of predictive model on traffic violations through data analytics enhancing road safety policies and transportation efficiency in Tacloban City Lean Jane Letrodo Elgera, Hilary Aniban Pestañas, Csharleen Angela Cruz Ramos, [and] Vanessa Ending Vidal; Noel B. Elizaga, adviser. Tacloban City Division of Management, University of the Philippines Tacloban College 2025. ix, 123 leaves illustrations 30 cm. text rdacontent unmediated rdamedia volume rdacarrier Undergraduate thesis (Bachelor of Science in Accountancy) -- University of the Philippines, Tacloban. This research paper can be made available to the general public-YES. This research paper can be accessed only after consultation with the author and research adviser-NO. This research paper can be accessed only by those bound by confidentiality agreement-NO. The growing urbanization and motorization in Tacloban City have contributed to a significant increase in traffic violations, posing persistent challenges to road safety, public order, and transportation efficiency. This study seeks to address these issues by developing a predictive model for traffic violations through data analytics, with the broader goal of supporting data-driven policymaking and enhancing local transportation systems. The study employed a number of datasets like historical traffic violation records, weather, fuel prices, and regulatory off-days data collected from government agencies. These datasets were subjected to a mix of statistical methods and machine learning algorithms like logistic regression, decision trees, and J48 classifiers. The analysis identified patterns of peak violation periods, thus enabling the development of targeted interventions and resource optimization strategies. One of the major outcomes of this research is the creation of a predictive model built into an operating application that functions as a useful decision-support system, providing insights for predicting traffic violation patterns. More so, it also promotes planning operations by facilitating the advance deployment of staff, maximizing the timing of action, and guiding the adjustment of infrastructure. The research underscored the utility of predictive analysis in urban transportation planning, offering empirical evidence in violation patterns. In general, the research shows the potential of evidence-based policymaking, enhanced transport efficiency, and improved road safety through data-driven methods in emerging cities such as Tacloban City. Predictive modeling of traffic violations Tacloban City. Pestañas, Hilary Aniban author. Ramos, Csharleen Angela Cruz author. Vidal, Vanessa Ending author. Elizaga, Noel B. adviser. Thesis FI UP UPTAC UPTAC LG 993.5 2025 A3 E45 Thesis