Investigating the efficacy of algorithmic student modelling in predicting students at risk of failing in tertiary education

The increasing numbers enrolling for college courses, and increased diversity in the classroom, poses a challenge for colleges in enabling all students achieve their potential. This paper reports on a study to model factors, using data mining techniques, that are predictive of college academic performance, and can be measured during first year enrolment. Data was gathered over three years, and focused on a diverse student population of first year students from a range of academic disciplines (n≈1100). Initial models generated on two years of data (n=713) demonstrate high accuracy. Advice is sought on additional analysis approaches to consider.

[1]  Zachary A. Pardos,et al.  The sum is greater than the parts: ensembling models of student knowledge in educational software , 2012, SKDD.

[2]  Simon Cassidy,et al.  Exploring individual differences as determining factors in student academic achievement in higher education , 2012 .

[3]  Brian C. Nelson,et al.  On Instructional Utility, Statistical Methodology, and the Added Value of ECD: Lessons Learned from the Special Issue , 2012, EDM 2012.

[4]  Mykola Pechenizkiy,et al.  Predicting Students Drop Out: A Case Study , 2009, EDM.

[5]  P. Pintrich.  A Manual for the Use of the Motivated Strategies for Learning Questionnaire (MSLQ). , 1991 .

[6]  Kristy J. Lauver,et al.  Do psychosocial and study skill factors predict college outcomes? A meta-analysis. , 2004, Psychological bulletin.

[7]  Ruth Woodfield,et al.  Individual differences and undergraduate academic success: the roles of personality, intelligence, and application , 2003 .

[8]  D. Duffin,et al.  Using ICT to enable inclusive teaching practices in higher education , 2009 .

[9]  M. A. Moran,et al.  The Leaving Certificate and first year university performance , 1979 .

[10]  Sebastián Ventura,et al.  Educational data mining: A survey from 1995 to 2005 , 2007, Expert Syst. Appl..

[11]  J. Biggs,et al.  The revised two-factor Study Process Questionnaire: R-SPQ-2F. , 2001, The British journal of educational psychology.

[12]  R. B. Sachin,et al.  A Survey and Future Vision of Data Mining in Educational Field , 2012, 2012 Second International Conference on Advanced Computing & Communication Technologies.

[13]  N. Delavari,et al.  A new model for using data mining technology in higher educational systems , 2004, Information Technology Based Proceedings of the FIfth International Conference onHigher Education and Training, 2004. ITHET 2004..

[14]  Ronan G. Reilly,et al.  Predicting introductory programming performance: A multi-institutional multivariate study , 2006, Comput. Sci. Educ..

[15]  Toon Calders,et al.  Introduction to the special section on educational data mining , 2012, SKDD.

[16]  Alex T. Ramsey,et al.  Cognitive and Non-Cognitive Predictors of College Readiness and Performance: Role of Academic Discipline. , 2013 .

[17]  Oliver Mooney,et al.  A study of progression in Irish higher education , 2010 .

[18]  Timothy J. Pleskac,et al.  Prediction of 4-year college student performance using cognitive and noncognitive predictors and the impact on demographic status of admitted students. , 2009, The Journal of applied psychology.

[19]  Neal Schmitt,et al.  Alternatives to GPA 1 Prediction of Four-Year College Student Performance using Cognitive and Noncognitive Predictors and the Impact on Demographic Status of Admitted Students , 2009 .

[20]  Neil T. Heffernan,et al.  Does Self-Discipline impact students' knowledge and learning? , 2009, EDM.

[21]  Serge Herzog,et al.  Estimating Student Retention and Degree-Completion Time: Decision Trees and Neural Networks Vis-a-Vis Regression. , 2006 .

[22]  Sebastián Ventura,et al.  Educational Data Mining: A Review of the State of the Art , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).