Understanding student motivation has long been a central concern in educational research. While
prior studies have extensively examined levels and correlates of motivation, far less is known
about the timing at which students transition into a state of complete motivational
disengagement. In present study, based on Cox proportional hazards modeling and using large-
scale data from the Programme for International Student Assessment (PISA), we develop a
computational simulation model to infer individual- and group-level distributions of academic
burnout onset across study weeks. Results demonstrate systematic variation in the timing of
academic burnout onset as a function of weekly study time, with longer study hours associated
with an earlier increase in burnout risk. To facilitate practical application, we further implement an
interactive ShinyApp that allows users to estimate academic burnout onset periods at the
individual, classroom, and school levels. This study contributes a novel methodological framework
for temporally locating motivational breakdown and offers a scalable tool for translating large-
scale assessment data into actionable educational insights.