Despite improved higher education accessibility in low and middle-income countries (LMICs), challenges persist in student drop-out, especially for socio-economically disadvantaged students. While machine learning models have enhanced our understanding of this challenge by predicting academic performance, many studies overlook LMIC-specific institutional factors or focus on specific courses, limiting their generalizability and policy uses. To address these issues, the authors compiled a comprehensive database using administrative and census data to predict undergraduate academic performance at the Pontifical Catholic University of Peru (PUCP). The study found that the most effective models were tree-based ensembles, particularly Random Forest, with key predictors including prior secondary school performance and university admission test scores. They present a high-performing model using o...

Despite improved higher education accessibility in low and middle-income countries (LMICs), challenges persist in student drop-out, especially for socio-economically disadvantaged students. While machine learning models have enhanced our understanding of this challenge by predicting academic performance, many studies overlook LMIC-specific institutional factors or focus on specific courses, limiting their generalizability and policy uses. To address these issues, the authors compiled a comprehensive database using administrative and census data to predict undergraduate academic performance at the Pontifical Catholic University of Peru (PUCP). The study found that the most effective models were tree-based ensembles, particularly Random Forest, with key predictors including prior secondary school performance and university admission test scores. They present a high-performing model using o...

Despite improved higher education accessibility in low and middle-income countries (LMICs), challenges persist in student drop-out, especially for socio-economically disadvantaged students. While machine learning models have enhanced our understanding of this challenge by predicting academic performance, many studies overlook LMIC-specific institutional factors or focus on specific courses, limiting their generalizability and policy uses. To address these issues, the authors compiled a comprehensive database using administrative and census data to predict undergraduate academic performance at the Pontifical Catholic University of Peru (PUCP). The study found that the most effective models were tree-based ensembles, particularly Random Forest, with key predictors including prior secondary school performance and university admission test scores. They present a high-performing model using o...

The simultaneous appearance in 1989 of the term “Washington Consensus” and the adoption of ILO Convention 169 are not a historical curiosity, but rather a milestone in the ambiguity of the recognition of collective rights of indigenous people. Now, while the political economy of Peruvian development has been described as “heavily centralised and ethnically define exclusionary” (Orihuela, 2020, p. 146), can it be said that it only obeys the weight of history? What characterized the political economy of recognition during a markedly neoliberal period? The aim of this essay is to outline a proposal for analysis of the type of political economy that governed the recognition of indigenous people’s rights in Peru during the Fujimori decade (1990-2000). Although the historical determinants of the condition of exclusion of these people, the characteristics of the Peruvian neoliberal pe...

Studies on the simultaneous relationships between monetary, multidimensional, and subjective poverty in low- and middle-income countries remain scarce and face critical limitations, including reliance on inaccurate monetary data, narrow non-monetary indicators, unclear poverty identification criteria, and limited focus on overlaps and joint incidences of poverty forms. Using data from the 2022 Peruvian National Household Survey, we address these gaps in five ways. First, we estimate monetary poverty using detailed household consumption data. Second, we measure multidimensional poverty across a comprehensive set of dimensions. Third, we establish clear identification criteria to determine who is poor according to the monetary, multidimensional, and subjective measures. Fourth, we analyze overlapping poverty patterns to identify subgroups experiencing multiple poverty forms. Fifth, we intr...