The rapid urbanization and development of smart cities necessitate innovative approaches to understand and enhance educational systems. This paper introduces a novel application of Topological Data Analysis (TDA) to the Programme for International Student Assessment (PISA) dataset, leveraging its ability to capture complex, nonlinear patterns within multidimensional data. By employing techniques such as VIETORIS-RIPS persistence, persistence entropy, and amplitude, we extract topological features that provide insights into student achievement within urban educational environments. Our analysis reveals distinct clusters of students characterized by their topological signatures, corresponding to various profiles of educational experiences in smart cities. Integrating these topological features with traditional data attributes enhances predictive models of student outcomes, demonstrating TDA’s potential as a powerful tool for sustainable urban educational research. This study contributes to methodological advancements in educational data analysis, offering actionable insights for policymakers and educators in smart cities to address disparities and promote excellence in student learning.