Chronic absenteeism remains a persistent equity challenge in California, yet traditional school- and district-level analyses often mask important variation within communities. This study develops a place-based approach to estimating chronic absenteeism risk at the ZIP code level, emphasizing the influence of local social, economic, and educational conditions on student attendance. Grounded in ecological systems theory and sociocultural theory, the study integrates publicly available educational, demographic, health, and socioeconomic data from 2020–2026. Correlation analysis, principal component analysis, and linear regression were used to identify key predictors and develop a predictive risk model with strong explanatory power (R² ≈ .86). Findings indicate that overcrowded housing, homelessness, student-reported sadness, and higher concentrations of Hispanic students and English learners are associated with increased absenteeism risk, while higher rates of fully credentialed teachers are associated with lower risk. Geospatial mapping revealed substantial variation within districts, highlighting underserved neighborhoods often obscured by aggregate data and informing more targeted, equitable interventions.
