A Comparative Analysis of Techniques for Predicting Student
Performance

D 2016

A Comparative Analysis of Techniques for Predicting Student Performance

BYDŽOVSKÁ, Hana

Základní údaje

Originální název

A Comparative Analysis of Techniques for Predicting Student Performance

Autoři

BYDŽOVSKÁ, Hana

Vydání

Raleigh, NC, USA, Proceedings of the 9th International Conference on Educational Data Mining, od s. 306-311, 6 s. 2016

Nakladatel

International Educational Data Mining Society

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Organizační jednotka

Fakulta informatiky

Klíčová slova anglicky

student performance prediction; student similarity; classification; regression; collaborative filtering

Štítky

best1, core_B, firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 10. 11. 2016 15:29, RNDr. Hana Bydžovská, Ph.D.

Anotace

V originále

The problem of student final grade prediction in a particular course has recently been addressed using data mining techniques. In this paper, we present two different approaches solving this task. Both approaches are validated on 138 courses which were offered to students of the Faculty of Informatics of Masaryk University between the years of 2010 and 2013. The first approach is based on classification and regression algorithms that search for patterns in study-related data and also data about students' social behavior. We prove that students’ social behavior characteristics improve prediction for a quarter of courses. The second approach is based on collaborative filtering techniques. We predict the final grades based on previous achievements of similar students. The results show that both approaches reached similar average results and can be beneficially utilized for student final grade prediction. The first approach reaches significantly better results for courses with a small number of students. In contrary, the second approach achieves significantly better results for mathematical courses. We also identified groups of courses for which we are not able to predict the grades reliably. Finally, we are able to correctly identify half of all failures (that constitute less than a quarter of all grades) and predict the final grades only with the error of one degree in the grade scale.

Návaznosti

MUNI/A/0945/2015, interní kód MU

Název: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace V.

Investor: Masarykova univerzita, Rozsáhlé výpočetní systémy: modely, aplikace a verifikace V., DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

Citovat

BYDŽOVSKÁ, Hana. A Comparative Analysis of Techniques for Predicting Student Performance. Online. In Tiffany Barnes, Min Chi, Mingyu Feng. Proceedings of the 9th International Conference on Educational Data Mining. Raleigh, NC, USA: International Educational Data Mining Society, 2016, s. 306-311.

@inproceedings{1345297,
   author = {Bydžovská, Hana},
   address = {Raleigh, NC, USA},
   booktitle = {Proceedings of the 9th International Conference on Educational Data Mining},
   editor = {Tiffany Barnes, Min Chi, Mingyu Feng},
   keywords = {student performance prediction; student similarity; classification; regression; collaborative filtering},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Raleigh, NC, USA},
   pages = {306-311},
   publisher = {International Educational Data Mining Society},
   title = {A Comparative Analysis of Techniques for Predicting Student Performance},
   year = {2016}
}

TY  - JOUR
ID  - 1345297
AU  - Bydžovská, Hana
PY  - 2016
TI  - A Comparative Analysis of Techniques for Predicting Student Performance
PB  - International Educational Data Mining Society
CY  - Raleigh, NC, USA
KW  - student performance prediction
KW  - student similarity
KW  - classification
KW  - regression
KW  - collaborative filtering
N2  - The problem of student final grade prediction in a particular course has recently been addressed using data mining techniques. In this paper, we present two different approaches solving this task. Both approaches are validated on 138 courses which were offered to students of the Faculty of Informatics of Masaryk University between the years of 2010 and 2013. The first approach is based on classification and regression algorithms that search for patterns in study-related data and also data about students' social behavior. We prove that students’ social behavior characteristics improve prediction for a quarter of courses. The second approach is based on collaborative filtering techniques. We predict the final grades based on previous achievements of similar students. The results show that both approaches reached similar average results and can be beneficially utilized for student final grade prediction. The first approach reaches significantly better results for courses with a small number of students. In contrary, the second approach achieves significantly better results for mathematical courses. We also identified groups of courses for which we are not able to predict the grades reliably. Finally, we are able to correctly identify half of all failures (that constitute less than a quarter of all grades) and predict the final grades only with the error of one degree in the grade scale.
ER  -

BYDŽOVSKÁ, Hana. A Comparative Analysis of Techniques for Predicting Student Performance. Online. In Tiffany Barnes, Min Chi, Mingyu Feng. \textit{Proceedings of the 9th International Conference on Educational Data Mining}. Raleigh, NC, USA: International Educational Data Mining Society, 2016, s.~306-311.

Podrobný výpis o publikaci