Alerta Escuela — Peru's National ML-Based School Dropout Early-Warning System

At the end of 2020, Peru's Ministry of Education (Minedu) launched Alerta Escuela, a nationwide web platform that uses a machine-learning model to estimate each student's risk of dropping out of school. Built with World Bank support, the model draws on administrative data — student characteristics, academic performance history, family context, school service characteristics and household socioeconomic information — to flag students at high, medium or low risk, giving school principals and tutors a dashboard for early intervention across Peru's initial, primary and secondary education levels.

What makes Alerta Escuela unusually well-documented is that Minedu and the World Bank did not stop at launching the tool — they rigorously evaluated it. A 2021–2023 implementation evaluation found that only 7% of schools with high- or medium-risk students actually accessed the platform, and just 2% downloaded its management and pedagogical guidelines; many school principals reported not understanding the model or the variables behind its risk scores, and found the tool "too time-consuming" because, in their view, it only requested information rather than offering solutions. A companion study tested SMS reminders grounded in behavioral-economics principles to nudge principals toward using the platform: the reminders significantly increased access to and use of the early-warning system, but that increased usage did not translate into more preventive action by school staff, and ultimately produced no measurable reduction in school dropout.

This is a genuinely mixed, evidence-rich case: a technically capable national ML system for an important problem, evaluated honestly, whose central finding is that better data access alone does not change front-line behavior or outcomes without simpler interfaces, clearer guidance, and stronger connectivity (36% of school facilities lacked reliable access). Peru continued to iterate on the platform after these findings, but the core lesson — that early-warning systems must be judged on downstream action and outcomes, not platform usage — is one of the more valuable evidence-based cautionary results in this catalogue.

Sources: World Bank Blogs (Alegría, Avitabile & Chumpitaz Torres, May 2023); Minedu / Peru's Ministry of Education repository (2022 methodology report; official launch announcement, gob.pe).

Read the full analysis: https://repositorio.minedu.gob.pe/handle/20.500.12799/8668