Abstract
Nowadays, health systems comprise a series of resources structured to provide healthcare services to meet our health needs. However, premature deaths still occur. To quantify and understand personal healthcare conditions affecting such amenable mortality, the Healthcare Access and Quality Index (HAQI) was put forward, evaluating 195 countries and territories since 1990. Nevertheless, the literature acknowledges a series of limitations of this framework, such as the drawbacks of using principal component analysis to aggregate individual indicators, the absence of control for financing and environmental conditions, and the presence of a substantial degree of data uncertainty. Accordingly, we propose a methodological alternative to the computation of the HAQI using a novel fuzzy Data Envelopment Analysis model to handle the aforementioned shortcomings. We also propose its extension towards the quantification of efficiency (E-HAQI) - in the sense of value for money - by incorporating financial aspects as modelling inputs. This way, we contribute with innovative modelling approaches that can also deal with the high degree of data uncertainty. Furthermore, in a second -stage analysis, the impact of key exogenous factors on healthcare access and quality is assessed via non -parametric hypothesis testing. Our results show positive and significant correlations of both the revisited HAQI and E-HAQI with the original HAQI 2016 dataset. They also reveal a better use of resources by European and Oceanian countries and territories than by Sub-Saharan African ones. Concerning contextual determinants, socio-demographic development, human development, and the type of health system were found to be statistically significant drivers of healthcare access and quality efficiency.

Abstract

Abstract

Abstract

Abstract
This study explores data mining techniques for predicting student dropout in higher education. The research compares different methodological approaches, including alternative algorithms and variations in model specifications. Additionally, we examine the impact of employing either a single model for all university programs or separate models per program. The performance of models with students grouped according to their position on the program study plan was also tested. The training datasets were explored with varying time series lengths (2, 4, 6, and 8 years) and the experiments use academic data from the University of Porto, spanning the academic years from 2012 to 2022. The algorithm that yielded the best results was XGBoost. The best predictions were obtained with models trained with two years of data, both with separate models for each program and with a single model. The findings highlight the potential of data mining approaches in predicting student dropout, offering valuable insights for higher education institutions aiming to improve student retention and success. © 2023 Associacao Portuguesa de Sistemas de Informacao. All rights reserved.