Naslov
Educational Data Driven Decision Making: Early Identification of Students at Risk by Means of Machine Learning

Autori
Kovač, Romano ; Oreški, Dijana

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of CECIIS 2018 / Strahonja, Vjeran ; Kirinić, Valentina - Varaždin, 2018, 231-236

Skup
29th Central European Conference on Information and Intelligent Systems (CECIIS 2018)

Mjesto i datum
Varaždin, Hrvatska, 19.09.2018. - 21.09.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Data-driven educational decision making, decision support system, machine learning, academic performance.

Sažetak
In the last few years there has been a notable increase in the data mining usage for educational purposes. Educational data mining is emerging field of research which has the aim of analysing data about students` activities. Prediction of student achievements is among the fastest growing research in this domain. Main goal of this paper is to provide useful knowledge to faculties and their management using data about students` activity at the LMS Moodle and comparing different machine learning techniques in order to analyse this data. In this paper we have evaluated four machine learning algorithms: neural networks, decision tree, support vector machines and logistic regression. Decision tree shown to be most accurate predictive model. Results indicated lecture and seminar attendance as significant predictors of academic success.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti

POVEZANOST RADA