Towards Student Success Prediction

D 2014

Towards Student Success Prediction

BYDŽOVSKÁ, Hana and Michal BRANDEJS

Basic information

Original name

Towards Student Success Prediction

Authors

BYDŽOVSKÁ, Hana (203 Czech Republic, belonging to the institution) and Michal BRANDEJS (203 Czech Republic, guarantor, belonging to the institution)

Edition

Portugal, Proceedings of the 6th International Conference on Knowledge Discovery and Information Retrieval - KDIR 2014, p. 162-169, 8 pp. 2014

Publisher

2014 SCITEPRESS – Science and Technology Publications

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Portugal

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

storage medium (CD, DVD, flash disk)

RIV identification code

RIV/00216224:14330/14:00076034

Organization unit

Faculty of Informatics

ISBN

978-989-758-048-2

Keywords in English

Recommender System; Social Network Analysis; Data Mining; Prediction; University Information System

Abstract

V originále

University information systems offer a vast amount of data which potentially contains additional hidden information and relations. Such knowledge can be used to improve the teaching and facilitate the educational process. In this paper, we introduce methods based on a data mining approach and a social network analysis to predict student grade performance. We focus on cases in which we can predict student success or failure with high accuracy. Machine learning algorithms can be employed with the average accuracy of 81.4%. We have defined rules based on grade averages of students and their friends that achieved the precision of 97% and the recall of 53%. We have also used rules based on study-related data where the best two achieved the precision of 96% and the recall was nearly 35%. The derived knowledge can be successfully utilized as a basis for a course enrollment recommender system.

Links

LG13010, research and development project

Name: Zastoupení ČR v European Research Consortium for Informatics and Mathematics (Acronym: ERCIM-CZ)

Investor: Ministry of Education, Youth and Sports of the CR

Citovat

BYDŽOVSKÁ, Hana and Michal BRANDEJS. Towards Student Success Prediction. In Ana Fred and Joaquim Filipe. Proceedings of the 6th International Conference on Knowledge Discovery and Information Retrieval - KDIR 2014. Portugal: 2014 SCITEPRESS – Science and Technology Publications, 2014, p. 162-169. ISBN 978-989-758-048-2.

@inproceedings{1193695,
   author = {Bydžovská, Hana and Brandejs, Michal},
   address = {Portugal},
   booktitle = {Proceedings of the 6th International Conference on Knowledge Discovery and Information Retrieval - KDIR 2014},
   editor = {Ana Fred and Joaquim Filipe},
   keywords = {Recommender System; Social Network Analysis; Data Mining; Prediction; University Information System},
   howpublished = {paměťový nosič},
   language = {eng},
   location = {Portugal},
   isbn = {978-989-758-048-2},
   pages = {162-169},
   publisher = {2014 SCITEPRESS – Science and Technology Publications},
   title = {Towards Student Success Prediction},
   year = {2014}
}

TY  - JOUR
ID  - 1193695
AU  - Bydžovská, Hana - Brandejs, Michal
PY  - 2014
TI  - Towards Student Success Prediction
PB  - 2014 SCITEPRESS – Science and Technology Publications
CY  - Portugal
SN  - 9789897580482
KW  - Recommender System
KW  - Social Network Analysis
KW  - Data Mining
KW  - Prediction
KW  - University Information System
N2  - University information systems offer a vast amount of data which potentially contains additional hidden information and relations. Such knowledge can be used to improve the teaching and facilitate the educational process. In this paper, we introduce methods based on a data mining approach and a social network analysis to predict student grade performance. We focus on cases in which we can predict student success or failure with high accuracy. Machine learning algorithms can be employed with the average accuracy of 81.4%. We have defined rules based on grade averages of students and their friends that achieved the precision of 97% and the recall of 53%. We have also used rules based on study-related data where the best two achieved the precision of 96% and the recall was nearly 35%. The derived knowledge can be successfully utilized as a basis for a course enrollment recommender system.
ER  -

BYDŽOVSKÁ, Hana and Michal BRANDEJS. Towards Student Success Prediction. In Ana Fred and Joaquim Filipe. \textit{Proceedings of the 6th International Conference on Knowledge Discovery and Information Retrieval - KDIR 2014}. Portugal: 2014 SCITEPRESS – Science and Technology Publications, 2014, p.~162-169. ISBN~978-989-758-048-2.

Detailed Information on Publication Record