Predicting students at risk of dropping out and intervening on them has become an important challenge, in which Artificial Intelligence techniques have shown promise. However, many teachers and other stakeholders are not experts in those techniques and face notable technical obstacles accessing them. To make Artificial Intelligence more accessible for the prediction of and the intervention on at-risk students, we propose the integration of Automated Machine Learning and Explainable Artificial Intelligence techniques into a Visual Interactive Dashboard to automate the entire process. Our objective is to allow non-expert users to easily obtain predictions from data that will help make decisions to avoid student dropout. Our dashboard tailored the interface providing two views (denoted basic and advanced) intended to be used for beginners and intermediate users respectively. In this paper we describe a case study in which a group of 49 users ran the Dashboard with a public dataset with the assignment to take action about student dropout. The Dashboard demonstrated promising performance. All the advanced interface users and 87.5
This article aims to discuss how the affective turn allows us to reconfigure our understanding of the migratory phenomenon. Based on the systematization of two research experiences conducted with migrants during their passage through Chiapas, it is argued that emotionality, pain, corporeality, and affect are essential dimensions for understanding human mobility. Using ethnographic and collaborative methodologies, and from a horizontal accompaniment approach, oral and graphic testimonies are made visible as forms of enunciation that denounce structural violence and open possibilities for symbolic and emotional agency. The conclusion is that emotions and bodies, far from being residual or anecdotal, emerge as spaces for knowledge production in contexts of international migration.
La presente investigación tuvo como objetivo principal determinar la relación entre el compromiso organizacional y la retención del talento humano en los colaboradores del sector financiero del Cantón Pujilí, Ecuador. Metodológicamente, adoptó un enfoque cuantitativo, no experimental, de corte transversal y alcance descriptivo-correlacional, aplicando un censo poblacional al 100% de la plantilla accesible, conformada por 116 profesionales activos de agencias bancarias y cooperativas de ahorro y crédito locales. La recolección de datos se realizó mediante dos cuestionarios validados en Google Forms que mostraron alta consistencia interna y validez: el de compromiso organizacional (17 ítems) alcanzó un Alfa de Cronbach de 0.920 y un KMO de 0.900, mientras que el de retención (9 ítems) obtuvo un Alfa de 0.902 y un KMO de 0.847. Los resultados descriptivos revelaron un escenario favorable donde predominó el nivel alto tanto en el compromiso organizacional (60.3%) como en la retención del talento (55.2%). Tras aplicar la prueba de Kolmogorov-Smirnov y determinar que los datos no siguen una distribución normal (p = 0.000), se empleó estadística no paramétrica mediante el coeficiente Rho de Spearman, arrojando un valor de Rho = 0.577 (p = 0.000) que evidencia una relación lineal positiva de intensidad moderada, concluyéndose que un mayor compromiso incrementa de manera directa y favorable la retención del personal en la identidad financiera local.
Official cadastral values in Latin American intermediate cities may fail to keep pace with rapidly changing asking-price patterns, weakening the responsiveness of local property-tax bases. This study introduces the Relative Gap Rate (TBR), defined as the proportional divergence between observed vacant-land asking prices and official cadastral values, and applies it to Ambato, Ecuador. A dataset of 182 georeferenced asking-price observations was interpolated across a common cantonal support of 19,231 hexagonal cells. Predictors comprised a hierarchically weighted Urban Vitality Index (UVI), distance to the structural road network, elevation, and traffic-incident count derived from 1787 records. The TBR surface exhibited very strong positive spatial autocorrelation (Moran’s I=0.956, p<0.001), while the discrete asking-price observations were also spatially autocorrelated (Moran’s I=0.282, p<0.001). Lagrange Multiplier diagnostics supported a Spatial Autoregressive specification (pseudo-R2=0.927; ρ=0.885). The Random Forest model achieved a test-set R2 of 0.8319 and an MAE of 5.3252, with UVI accounting for 64.37% of impurity-based feature importance. The median TBR was 6.0, meaning that the median asking price was seven times the corresponding cadastral value; the maximum TBR reached 43.0. Traffic-incident count retained a positive spatial-regression coefficient but contributed only 5.53% of Random Forest importance. The framework provides an adaptable municipal diagnostic for identifying cadastral–asking-price divergence, subject to local validation and city-specific calibration.
La dispersión entre los precios unitarios de los edificios se entendería normal ya que no existen dos proyectos iguales; no obstante, se demuestra que la dispersión en los precios tiende a disminuir conforme el nivel de detalle del nombre del rubro (NDN) se incrementa. Por lo expuesto se obtienen diferentes bases de datos de precios unitarios de proyectos en Ecuador de los últimos cinco años, para analizar la relación entre el NDN con la variación en los precios, además, los resultados son analizados y discutidos en referencia a variables como ubicación, año de ejecución y tipo de obra. Se destaca que los hallazgos contribuyen por un lado una guía para generar nombres de rubros de construcción que deriven en estimación de costos más precisas y justas. Asimismo, aportan argumentos técnicos a los organismos de control para determinar posibles subestimaciones o sobreestimaciones de precios.
