Title: Educational data mining for predicting students' success Authors:  Marialuisa Restaino - University of Salerno (Italy) [presenting]
Marcella Niglio - University of Salerno (Italy)
Michele La Rocca - University of Salerno (Italy)
Maria Prosperina Vitale - University of Salerno (Italy)
Abstract: Educational Data Mining (EDM) is an emerging research field that focuses on the application of techniques and methods of data mining in educational environments. The focus is on "student success", intended as the ability of students to close a given educational level successfully. It is a crucial element of evaluation, and it is often used as a criterion to assess the quality and performance of educational institutions. Early detection of the "students at risk" (with a high probability of dropping out of the educational institution) and the adoption of preventive measures can help decision-makers to provide and plan proper actions for improving students' performances (and consequently their success), and eventually revise the educational project. The aim is to explore the main differences in students' performance among bachelor's degrees by using regression models. The analysis concerns students enrolled at 3-year degrees in an Italian university (located in the South of Italy) during ten academic years. Student success is measured in terms of the number of ECTS credits earned during the first year. Hence, the main purposes are to i) estimate the probability of getting at least a certain number of credits at the end of the first year, ii) identify which students' features might affect it, and iii) classify students according to their churn risk.