This study focuses on improving the predictive power of early warning systems (EWSs) to decrease chronic absenteeism in early childhood. Using a demographically diverse sample of students followed from PreK to third grade in Boston Public Schools (N = 6,698), we demonstrate how and why two modern machine learning (ML) algorithms—the Synthetic Minority Oversampling Technique (SMOTE) and Extreme Gradient Boosting (XGBoost)—can enhance EWS accuracy. The best-performing XGBoost model with SMOTE achieved a 54-percentage point improvement in accuracy (in terms of recall rate) over the logistic regression model closest to those used in current EWSs, more accurately detecting students who would become chronically absent in third grade, and outperformed other ML approaches evaluated. Notably, models excluding student demographic information maintained comparable predictive accuracy.
AllensworthE. M.BalfanzR.RogersT.DemarziJ. (2021). Absent from school: Understanding and addressing student absenteeism. Harvard Education Press.
2.
AllensworthE. M.EastonJ. Q. (2007). What matters for staying on-track and graduating in Chicago Public High Schools: A close look at course grades, failures, and attendance in the freshman year (Research report). Consortium on Chicago School Research.
3.
AllisonM. A.AttishaE.LernerM.De PintoC. D.BeersN. S.GibsonE. J.GorskiP.KjolhedeC.O’LearyS. C.SchumacherH.Weiss-HarrisonA. (2019). The link between school attendance and good health. Pediatrics, 143(2), 1–13.
4.
AnsariA.GottfriedM. A. (2021). The grade-level and cumulative outcomes of absenteeism. Child Development, 92(4), e548–e564.
5.
BakerR. S.EsbenshadeL.VitaleJ.KarumbaiahS. (2023). Using demographic data as predictor variables: A questionable choice. Journal of Educational Data Mining, 15(2), 22–52.
6.
BalfanzR.ByrnesV. (2012). The importance of being in school: A report on absenteeism in the nation’s public schools. The Education Digest, 78(2), 4–9.
7.
BalfanzR.ByrnesV. (2013). Meeting the challenge of combating chronic absenteeism (pp. 1–2). Everyone Graduates Center at Johns Hopkins University School of Education.
8.
BalfanzR.ByrnesV. (2019). Early warning indicators and intervention systems: State of the field. In FredricksJ. A.ReschlyA. L.ChristensonS. L. (Eds.), Handbook of student engagement interventions (pp. 45–55). Academic Press.
BirdK. A.CastlemanB. L.MabelZ.SongY. (2021). Bringing transparency to predictive analytics: A systematic comparison of predictive modeling methods in higher education. Aera Open, 7, 233285842110376.
11.
Boston Public Schools. (2022). Attendance and punctuality policies and procedures. Superintendent’s Circular: School Year 2022–2023.
12.
ChangH. N.RomeroM. (2008). Present, engaged, and accounted for: The critical importance of addressing chronic absence in the early grades (Report). National Center for Children in Poverty.
13.
ChawlaN. V.BowyerK. W.HallL. O.KegelmeyerW. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357.
14.
ChenT.GuestrinC. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, United States (pp. 785–794). Association for Computing Machinery.
15.
ChristieS. T.JarrattD. C.OlsonL. A.TaijalaT. T. (2019). Machine-learned school dropout early warning at scale. International Educational Data Mining Society.
DeussenT.HansonH.BishtB. (2017). Are two commonly used early warning indicators accurate predictors of dropout for English learner students? Evidence from six districts in Washington State (REL 2017-261). Regional Educational Laboratory Northwest.
18.
DworkC.HardtM.PitassiT.ReingoldO.ZemelR. (2012, January). Fairness through awareness. Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, Cambridge, MA, United States (pp. 214–226). Association for Computing Machinery.
19.
EhrlichS. B.GwynneJ. A.AllensworthE. M. (2018). Pre-kindergarten attendance matters: Early chronic absence patterns and relationships to learning outcomes. Early Childhood Research Quarterly, 44, 136–151.
20.
EhrlichS. B.GwynneJ. A.ParejaA. S.AllensworthE. M. (2013). Preschool attendance in Chicago Public Schools: Relationships with learning outcomes and reasons for absences. University of Chicago Consortium on Chicago School Research.
21.
FariaA. M.SorensenN.HeppenJ.BowdonJ.TaylorS.EisnerR.FosterS. (2017). Getting students on track for graduation: Impacts of the early warning intervention and monitoring system after one year (pp. 1–82; REL 2017-272). Regional Educational Laboratory Midwest.
22.
FeldmanM.FriedlerS. A.MoellerJ.ScheideggerC.VenkatasubramanianS. (2015). Certifying and removing disparate impact. Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia (pp. 259–268). Association for Computing Machinery.
23.
Fernández-DelgadoM.CernadasE.BarroS.AmorimD. (2014). Do we need hundreds of classifiers to solve real world classification problems?Journal of Machine Learning Research, 15, 3133–3181.
24.
FreundY.SchapireR. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139.
25.
FuchsD.ComptonD. L.FuchsL. S.BryantJ.DavisG. N. (2008). Making “secondary intervention” work in a three-tier responsiveness-to-intervention model: Findings from the first-grade longitudinal reading study of the National Research Center on Learning Disabilities. Reading and Writing, 21, 413–436.
26.
FuchsL. S.FuchsD.HamlettC. L. (2007). Using curriculum-based measurement to inform reading instruction. Reading and Writing, 20(6), 553–567.
27.
GándaraD.AnahidehH.IsonM. P.PicchiariniL. (2024). Inside the Black Box: Detecting and mitigating algorithmic bias across racialized groups in college student-success prediction. AERA Open, 10, 1–15. https://doi.org/10.1177/23328584241258741
28.
GholamyA.KreinovichV.KoshelevaO. (2018). Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation (Technical report UTEP-CS-18-09). University of Texas at El Paso. https://scholarworks.utep.edu/cs_techrep/1209/
29.
GottfriedM. A. (2014). Chronic absenteeism and its effects on students’ academic and socioemotional outcomes. Journal of Education for Students Placed at Risk (JESPAR), 19(2), 53–75.
30.
GottfriedM. A.HuttE. L. (2019). Addressing absenteeism: Lessons for policy and practice. Policy Analysis for California Education (PACE).
31.
HardtM.PriceE.SrebroN. (2016). Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems, 29, 3315–3323.
32.
HastieT.TibshiraniR.FriedmanJ. H.FriedmanJ. H. (2009). The elements of statistical learning: Data mining, inference, and prediction. Springer.
33.
HeckmanJ. J. (2008). The case for investing in disadvantaged young children. CESifo DICE Report, 6(2), 3–8.
34.
HeppenJ. B.KurkiA.BrownS. (2020). Can texting parents improve attendance in elementary school? A test of an adaptive messaging strategy (Appendix; NCEE 2020-006a). National Center for Education Evaluation and Regional Assistance.
35.
HosmerD.W.LemeshowS. (2000). Applied logistic regression. John Wiley and Sons.
JacobsenW. C.PaceG. T.RamirezN. G. (2019). Punishment and inequality at an early age: Exclusionary discipline in elementary school. Social Forces, 97(3), 973–998.
38.
KabayS.WeilandC.YoshikawaH. (2020). Costs of the Boston public prekindergarten program. Journal of Research on Educational Effectiveness, 13(4), 574–600.
KeG.MengQ.FinleyT.WangT.ChenW.MaW.YeQ.LiuT.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In GuyonI.LuxburgU. V.BengioS.WallachH.FergusR.VishwanathanS.GarnettR. (Eds.), Advances in neural information processing systems, Long Beach, CA, United States (Vol. 30, pp. 3146–3154). Curran Associates, Inc.
43.
KearneyC. A.GonzálvezC.GraczykP. A.FornanderM. J. (2019). Reconciling contemporary approaches to school attendance and school absenteeism: Toward promotion and nimble response, global policy review and implementation, and future adaptability (Part 1). Frontiers in Psychology, 10, 1–16.
44.
KleinM.SosuE. M.DareS. (2020). Mapping inequalities in school attendance: The relationship between dimensions of socioeconomic status and forms of school absence. Children and Youth Services Review, 118, 1–12.
45.
LeeS.ChungJ. Y. (2019). The machine learning-based dropout early warning system for improving the performance of dropout prediction. Applied Sciences, 9(15), 1–14.
46.
LundbergS. M.LeeS. I. (2017). A unified approach to interpreting model predictions. In GuyonI.LuxburgU. V.BengioS.WallachH.FergusR.VishwanathanS.GarnettR. (Eds.), Advances in neural information processing systems (Vol. 30, pp. 4765–4774). Curran Associates, Inc.
Massachusetts Department of Elementary and Secondary Education & American Institutes for Research. (2013). Technical descriptions of risk model development: Early and late elementary age groupings (Grades 1–6). Massachusetts Early Warning Indicator System (EWIS). https://www.doe.mass.edu/ccte/sec-supports/ewis/default.html
OECD. (2020). Case study: Massachusetts’ (United States) Early Warning Indicator System (EWIS). Strengthening the Governance of Skills Systems: Lessons From Six OECD Countries, OECD iLibrary. https://doi.org/10.1787/1fbfc1a3-en
PengC. Y. J.LeeK. L.IngersollG. M. (2002). An introduction to logistic regression analysis and reporting. The Journal of Educational Research, 96(1), 3–14.
53.
PurtellK. M.AnsariA. (2022). Why are children absent from preschool? A nationally representative analysis of Head Start programs. Frontiers in Education, 7, 1–13.
54.
RogersT.FellerA. (2018). Reducing student absences at scale by targeting parents’ misbeliefs. Nature Human Behaviour, 2(5), 335–342.
55.
RomeroM.LeeY. S. (2007). A national portrait of chronic absenteeism in the early grades (pp. 1–8). National Center for Children in Poverty, Columbia University.
56.
SansoneD. (2019). Beyond early warning indicators: High school dropout and machine learning. Oxford Bulletin of Economics and Statistics, 81(2), 456–485.
SheldonS. B. (2007). Improving student attendance with school, family and community partnerships. The Journal of Educational Research, 100(5), 267–275.
TantithamthavornC.HassanA. E.MatsumotoK. (2018). The impact of class rebalancing techniques on the performance and interpretation of defect prediction models. IEEE Transactions on Software Engineering, 46(11), 1200–1219.
Van BuurenS.Groothuis-OudshoornK. (2011). Mice: Multivariate imputation by chained equations in R. Journal of Statistical Software, 45, 1–67.
64.
WeiW. (2024). Exploring patterns of absenteeism from prekindergarten through early elementary school and their associations with children’s academic outcomes. AERA Open, 10, 1–15.
65.
WeissmanA. (2022). Friend or foe? The role of machine learning in education policy research [Doctoral thesis, University of Michigan].
WilliamsH. D. (1927). Truancy and delinquency. Journal of Applied Psychology, 11(4), 276–288.
69.
WuT.WeilandC.DiemerM. A.UntermanR.ShapiroA.StainesT. (2025). Measuring “noncognitive” skills at scale: Building longitudinal student behavior composites using administrative data (EdWorkingPaper: 25-1250). Annenberg Institute at Brown University. https://doi.org/10.26300/7h7f-0j56
70.
WuT.WeilandC.StainesT. (2026). The chronic(les) of absenteeism measurement: Unpacking the many measures of attendance and evidence for a lower chronic absenteeism threshold (EdWorkingPaper: 26-1380). Annenberg Institute at Brown University. https://doi.org/10.26300/1zvw-qw93
71.
YuR.LeeH.KizilcecR. F. (2021, June). Should college dropout prediction models include protected attributes?Proceedings of the Eighth ACM Conference on Learning@ Scale (pp. 91–100). Virtual Event, Germany. Association for Computing Machinery.
72.
ZafarM. B.ValeraI.RogriguezM. G.GummadiK. P. (2017, April). Fairness constraints: Mechanisms for fair classification. In SinghA.ZhuJ. (Eds.), Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (pp. 962–970). PMLR.
73.
ZhouZ. H. (2012). Ensemble methods: Foundations and algorithms. CRC Press.
