Purpose: The prediction of student attrition is critical to facilitate retention mechanisms. This study aims to focus on implementing a method to predict student attrition in the upper years of a physiotherapy program.Design/methodology/approach: Machine learning is a computer tool that can recognize patterns and generate predictive models. Using a quantitative research methodology, a database of 336 university students in their upper-year courses was accessed. The participant's data were collected from the Financial Academic Management and Administration System and a platform of Universidad Autónoma de Chile. Five quantitative and 11 qualitative variables were chosen, associated with university student attrition. With this database, 23 classifiers were tested based on supervised machine learning.Findings: About 23.58% of males and 17.39% of females were among the attrition student group. The mean accuracy of the classifiers increased based on the number of variables used for the training. The best accuracy level was obtained using the “Subspace KNN” algorithm (86.3%). The classifier “RUSboosted trees” yielded the lowest number of false negatives and the higher sensitivity of the algorithms used (78%) as well as a specificity of 86%.Practical implications: This predictive method identifies attrition students in the university program and could be used to improve student retention in higher grades.Originality/value: The study has developed a novel predictive model of student attrition from upper-year courses, useful for unbalanced databases with a lower number of attrition students.

Air pollution stands as a primary environmental factor influencing mortality globally. Despite its significance, individuals frequently struggle to assess the risks associated with polluted environments. This paper delves into the psychological mechanisms that contribute to the discrepancy between public perception of air quality and objective measurements. Through an extensive literature review spanning several decades, six fundamental heuristics that underpin misperceptions of air quality are identified and examined. The article further explores the theoretical and practical implications of acknowledging these biases in the development of urban environmental policies. By addressing judgmental biases, urban planners can improve the communication of risk information among lay people and ensure that environmental improvements are acknowledged and valued by all members of the community.

Wood-burning pollution is a severe problem in southern Chile, where every winter, people are exposed to unhealthy ambient fine particulate matter (PM_2.5) concentrations. Urban air quality is a major concern for health officials, but public awareness campaigns tend to focus on outdoor hazards. Our understanding of how residents are exposed and perceive air pollution risks in their homes remains incomplete. This study explores the ability of participants to perceive indoor air quality. We collected data on 81 households, combining perceptions of air quality with objective measurements of PM_2.5. Residents’ evaluations of air quality were systematically compared to inspectors’ evaluations in order to examine the home halo effect. We found that residents tended to overestimate air quality in their homes. We discuss how our data supported the existence of a home halo effect, but also point out the possibility that individuals’ ability to perceive air quality in indoor spaces is limited by other factors.