Auto-generated ensemble model for predicting student success

U. Braendle, H. Zeineddine, A. Farah

Publikation: KonferenzbeitragPapierBegutachtung

Abstract

Students' success has recently become a primary strategic objective for most intuitions of higher education. With budget cuts and ramping operational costs, universities are paying more attention to sustaining students' enrollment in their programs without compromising rigor and quality of education. Many of those universities have dedicated special units in their organizational structures to look after that objective. Traditionally, academic institutions have relied on data collected from registrar's transcripts, academic units' feedback, faculty's alert, and from interaction with students. With the proliferation of big data analytics and Machine Learning, universities are increasingly relying on students' data to predict students' performance. Many initiatives and research projects addressed the use of students' behavioral and academic data in their first academic year to classify students and predict their future performance using advanced statistical models. However, little work has been done to predict academic performance through machine learning. In this paper, we propose the use of automatic search in Machine Learning to identify the best model to predict student performance using data available prior to the start of the academic program. © 2019 Association for Computing Machinery. ACM
OriginalspracheEnglisch
Seiten23:1-23:4
Seitenumfang4
DOIs
PublikationsstatusVeröffentlicht - 2 Dez. 2019
Extern publiziertJa

Fingerprint

Untersuchen Sie die Forschungsthemen von „Auto-generated ensemble model for predicting student success“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren