In today's education, school success is defined as ensuring achievement for every student. To reach this goal, educators need tools to help them identify students who are at risk academically and adjust instructional strategies to better meet these students' needs. Student progress monitoring is a practice that helps teachers use student performance data to continually evaluate the effectiveness of their teaching and make more informed instructional decisions. This paper reflects the main output of the SPEET project as an IT tool that implements specific algorithms developed to deal with the basic problems tackled in the project: Classification, Clustering and Drop-out Prediction.
|Titolo:||Data-driven tool for monitoring of students performance|
|Data di pubblicazione:||2019|
|Appare nelle tipologie:||04.1 Contributo in Atti di convegno|