Pregled bibliografske jedinice broj: 1078238
Development and comparison of predictive models based on learning management system data
Development and comparison of predictive models based on learning management system data // WSEAS TRANSACTIONS on INFORMATION SCIENCE and APPLICATIONS, 16 (2019), 192-201 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1078238 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Development and comparison of predictive models
based on learning management system data
Autori
Oreški, Dijana ; Hajdin, Goran
Izvornik
WSEAS TRANSACTIONS on INFORMATION SCIENCE and APPLICATIONS (1790-0832) 16
(2019);
192-201
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
data preparation, feature reduction, machine learning, neural networks, academic performance, student success.
Sažetak
This study introduces and evaluates different feature reduction and supervised machine learning approaches to predict the students` academic success. Our analysis is based on data about students` activities in the learning management system. We found that neural networks based approach with principal component analysis in feature reduction is the most effective for learning management system data.
Izvorni jezik
Engleski
Znanstvena područja
Informacijske i komunikacijske znanosti, Interdisciplinarne društvene znanosti
POVEZANOST RADA
Ustanove:
Fakultet organizacije i informatike, Varaždin
