Learn more about the theoretical underpinnings of
our comprehensive college dropout prediction model
College dropout is a growing problem. Approximately 25% of students who enroll in tertiary institutions in Chile withdraw from their academic programs during their first academic year. Early detection of students at risk of dropping out is an effective measure to address this phenomenon.
Evolution of college dropout rates in Chile (2008 – 2022)
(Based on data from Consejo Nacional de Educación, n.d.)
Combining Multiple Psychosocial and Study Skill Factors and
Traditional Predictors to Predict Retention (Robbins, 2004).
While college dropout is significantly influenced by a combination of academic performance, socioeconomic status, and personal and institutional characteristics, a combination of demographic, socioeconomic, cognitive, non-cognitive, and integrative factors may better predict dropout intentions.
In order to overcome the unidimensional understanding and addressing of the phenomenon of college dropout, we developed a flexible, holistic model that includes demographic and academic characteristics of students, as well as factors of life experiences, psychological and social integration to college life.
Sample of the factors considered in the elaboration of the
comprehensive predictive model of university dropout.
Combining Multiple Psychosocial and Study Skill Factors and
Traditional Predictors to Predict Retention (Robbins, 2004).
Our analytical model for college dropout prediction is a comprehensive tool that integrates insights from the fields of education, psychometrics, and statistics. This multidisciplinary approach allows the model to capture the complexity of the college dropout phenomenon and provide valuable predictions that can inform intervention strategies.
Adaptiva Early Warning System® (AEWS) is a student success system that allows faculty to provide meaningful feedback to students based on predictive models. The premise behind AEWS is to utilize students data to determine which students might be at risk in real time. Large data sets are mined through analytics, and statistical techniques are applied to predict which students might fall behind.
Sample of Adaptiva Early Warning System® Student Dashboard.
We are a remote-first team with offices in Santiago, Chile.
Tell us about your project!
