Vol 7. No. 3 - September, 2014 African Journal of Computing & ICT © 2014 Afr J Comp & ICT – All Rights Reserved - ISSN 2006-1781 www.ajocict.net 21 A Multi-Gene Genetic Programming Application for Predicting Students Failure at School J.O. Orove Department of Computer Science University of Port Harcourt Rivers State, Nigeria E-mail: joshuaorove2012@gmail.com Tel: +234 7067992097 N.E. Osegi Department of Information and Communication Technology National Open University of Nigeria Lagos State, Nigeria E-mail: geeqwam@gmail.com Tel: +234 7030081615 Website: www.osegi.com B.O. Eke Department of Computer Science University of Port Harcourt Rivers State, Nigeria E-mail:bathoyol@gmail.com Tel: +234 8037049586 ABSTRACT Several efforts to predict student failure rate (SFR) at school accurately still remains a core problem area faced by many in the educational sector. The procedure for forecasting SFR are rigid and most often times require data scaling or conversion into binary form such as is the case of the logistic model which may lead to lose of information and effect size attenuation. Also, the high number of factors, incomplete and unbalanced dataset, and black boxing issues as in Artificial Neural Networks and Fuzzy logic systems exposes the need for more efficient tools. Currently the application of Genetic Programming (GP) holds great promises and has produced tremendous positive results in different sectors. In this regard, this study developed GPSFARPS, a software application to provide a robust solution to the prediction of SFR using an evolutionary algorithm known as multi-gene genetic programming. The approach is validated by feeding a testing data set to the evolved GP models. Result obtained from GPSFARPS simulations show its unique ability to evolve a suitable failure rate expression with a fast convergence at 30 generations from a maximum specified generation of 500. The multi-gene system was also able to minimize the evolved model expression and accurately predict student failure rate using a subset of the original expression. Keywords: Genetic Programming, Student Failure Rate, Multi-Gene GP. African Journal of Computing & ICT Reference Format: J.O. Orove, N.E. Osegi & B.O. Eke (2014). A Multi-Gene Genetic Programming Application for Predicting Students Failure at School. Afr J. of Comp & ICTs. Vol 7, No. 3. Pp21-34. 1. INTRODUCTION SFR has always being and will continue to be a major concern to stakeholders in the educational sector. It refers to the proportion (or more correctly percentage) of students not graduating in a chosen course of study [1]. It is an important aspect of educational curricula assessment as this will help educational administrators to evaluate the performance of their existing curricula, teaching system, infrastructure and student relations programmes. Since the performance of any school system is largely affected by the failure rate of the students, it becomes necessary to study this obviously very important parameter. In particular, there has been a global call to reduce the failure rates of science school students, especially in the Mathematics courses [2]. Social graphs and data mining techniques [3, 4] have been suggested and some cases. Logistic and multiple linear regression techniques have also been used to study student failures rates [5, 14]. Methodologies for investigating student failure rates or decline in academic performance using artificial intelligence techniques such as Neuro- Genetic Algorithms (NGAs), Artificial Neural Networks (ANNs), Genetic Algorithms and decision trees [6,7,8, 9], have been suggested and developed in the literature.