Predictive Model of the Dropout Intention of Learners in Public High Schools in Valenzuela City
DOI:
https://doi.org/10.65339/ijsair.V2.I2.643Keywords:
Academic Burnout, Dropout Intention, Family Strain, Multinomial Logistic Regression, Negative School Pressure, Predictive Model, Public Junior High School Learners, Risk Indicators, Valenzuela CityAbstract
This study developed a predictive model of dropout intention among public junior high school learners in Valenzuela City by examining demographic characteristics, dropout-related factor domains, and selected dropout-related risk indicators. Anchored on the Theory of Planned Behavior, the study conceptualized dropout intention as an early indicator of potential school withdrawal and a basis for preventive intervention. A quantitative correlational-predictive research design was employed involving 4,653 Grades 7–10 learners enrolled in public secondary schools in Valenzuela City during School Year 2025–2026. Data were gathered using the researcher-developed Dropout Intention Assessment Questionnaire (DIAQ) and analyzed through descriptive statistics, Spearman’s Rank-Order Correlation, and Multinomial Logistic Regression. Results showed that Family Strain was the most prominent dropout-related factor, while Environmental Factors, Academic Burnout, and Negative School Pressure were present at moderate levels. Most learners demonstrated very low dropout intention, although a small proportion exhibited moderate to very high levels, indicating vulnerability to disengagement. Correlation analysis revealed that all dropout-related factor domains were significantly and positively associated with dropout intention. Multinomial logistic regression identified Academic Burnout as the strongest and most consistent predictor, followed by Family Strain, Negative School Pressure, grade retention, chronic absenteeism, academic failure, working student status, bullying experience, health-related absenteeism, and low parental educational attainment. The final model significantly improved predictive accuracy and demonstrated acceptable explanatory power for classifying learners according to dropout intention levels. The findings indicate that dropout intention is influenced by multiple interacting academic, family, school, and personal factors and that predictive analytics can support early identification and intervention efforts for learners at risk. The study aligns with Sustainable Development Goal (SDG) 4 on Quality Education and SDG 10 on Reduced Inequalities by promoting learner retention, educational continuity, and equitable access to educational opportunities. Its sustainability contribution lies in strengthening educational, institutional, and socio-economic sustainability through evidence-based learner support and data-informed dropout prevention initiatives.
References
Ajzen, I. (1991). The theory of planned behavior. Organizational Behavior and Human Decision Processes, 50(2), 179–211.
Balfanz, R., & Byrnes, V. (2019). Early warning indicators and intervention systems: State of the field. In J. A. Fredricks, A. L. Reschly, & S. L. Christenson (Eds.), Handbook of student engagement interventions: Working with disengaged students. Academic Press.
Banaag, R. A., Sumodevilla, J. L. C., & Potane, J. D. (2024). Factors affecting student drop-out behavior: A systematic review. International Journal of Educational Management and Innovation, 5(1), 53–70.
Butawan, J. S. (2020). Project (SEB): Sagip Estudyanteng Bulihan—An intervention program to reduced dropout rate in Bulihan Integrated National High School. International Journal of Innovative Science and Research Technology, 5(12).
Chirteş, G. (2010). A case study into the causes of school dropout. Acta Didactica Napocensia, 3(4), 25–34.
Colorado Department of Education. (n.d.). On-track/early warning systems. Colorado Dropout Prevention Framework. Retrieved April 6, 2026.
Daligcon, M. C. B., Nocasa, R. A., & Nocas, W. C. (2019). Predictors of students at-risk of dropping out (SARDO) in Pangasinan II: Basis for a strategic intervention program. E-Saliksik: Department of Education Research Portal (Research bulletin; posted January 23, 2024).
Department of Education. (2010). DO 74, s. 2010: Guidelines on mainstreaming the Dropout Reduction Program (DORP) in the public secondary schools.
Department of Education–National Capital Region. (2022). Technical Assistance for Learners At-Risk of Dropping Out (TALA) (Regional Memorandum NCR No. 033, s. 2022).
Department of Education–National Capital Region. (2023). Technical assistance management (Regional Memorandum No. 449, s. 2023).
Findeisen, S., Brodsky, A., Michaelis, C., Schimmelpenningh, B., & Seifried, J. (2024). Dropout intention: A valid predictor of actual dropout? Empirical Research in Vocational Education and Training, 16, Article 10.
Franklin, B. J., & Trouard, S. B. (2014). An analysis of dropout predictors within a state high school graduation panel. Schooling, 5(1), 1–8.
Herrin, A. N., Alegado, J. L. G., Borja, J. B., Mayol, N. L., Largo, F. M., Bas, I. N., & Abrigo, M. R. M. (2024). Examining the role of bullying on schooling outcomes: Findings from the Longitudinal Cohort Study on the Filipino Child (PIDS Discussion Paper Series No. 2024-42). Philippine Institute for Development Studies.
Jobs for the Future. (2014, February). Early warning indicators and segmentation analysis: A technical guide on data studies that inform dropout prevention and recovery.
Muñoz-Inostroza, K., López-Angulo, Y., Sáez-Delgado, F., Pinto-Vigueras, J., Melo-Moreno, P., & Bernardo, A. B. (2024). Measuring dropout intention in college students: A systematic literature review. Journal of Higher Education Theory and Practice, 24(6).
Orion, H. C., Jr., Forosuelo, E. J. D., & Cavalida, J. M. (2014). Factors affecting students’ decision to drop out of school. SLONGAN, 2(1).
Parreño, S. J. (2023). School dropouts in the Philippines: Causes, changes and statistics. Sapienza: International Journal of Interdisciplinary Studies, 4(1), e23002.
Rabelo, A. M., & Zárate, L. A. (2025). A model for predicting dropout of higher education students. Data Science and Management, 8(1), 72–85.
Second Congressional Commission on Education (EDCOM II). (2024). Miseducation: The failed system of Philippine education (EDCOM II year one report).
Second Congressional Commission on Education (EDCOM II). (2025). Fixing the foundations: A matter of national survival (EDCOM II year two report).
Second Congressional Commission on Education (EDCOM II). (2026). Turning point: A decade of necessary reforms (The EDCOM II final report).
Seo, E.-Y., Yang, J., Lee, J.-E., & So, G. (2024). Predictive modelling of student dropout risk: Practical insights from a South Korean distance university. Heliyon, 10(11), e30960.
Trivino, J. T., Tiongzon, B. D., Barazon, L. M., Jr., & Inocian, E. P. (2017). Family, individual, community and school profile analysis of learners at risk of dropping out in Cebu. Zenodo.
Ujkani, B., Minkovska, D., & Stoyanova, L. (2022). Application of logistic regression technique for predicting student dropout. In Proceedings of the XXXI International Scientific Conference Electronics (ET2022) (pp. 1–4). IEEE.
Véliz Palomino, J. C., & Ortega, A. M. (2023). Dropout intentions in higher education: Systematic literature review. Journal on Efficiency and Responsibility in Education and Science, 16(2), 149–158.
Venkatesan, R. G., Karmegam, D., & Mappillairaju, B. (2024). Exploring statistical approaches for predicting student dropout in education: A systematic review and meta-analysis. Journal of Computational Social Science, 7, 171–196.
