Large volume of educational data has led to more challenging in predicting student's performance. In Malaysia currently, study about the performance of students in Malaysia institutions is very little being addressed. The previous studies are still insufficient to identify what factors contribute to student's achievements and lack of investigations on exploring pattern of student's behaviour that affecting their academic performance within Malaysia context. Therefore, predicting student's academic performance by using decision trees is proposed to improve student's achievements more effectively. The main objective of this paper is to provide an overview on predicting student's academic performance using by using data mining techniques. This paper also focuses on identifying the pattern of student's behaviour and the most important attributes that impact to the student's achievement. By using educational data mining techniques, the students, lecturers and academic institution are able to have a better understanding on the student's achievement.
Copula become a popular tool to measure the dependency between financial data due to its ability to capture the non-normal distributions. Hence, this paper will inspect the impact of input models towards the parameter estimation of marginal and copula models for KLCI and FBMHS returns series by considering the ARMA-GARCH model and the ARMA-EGARCH model. This study also investigates the dependency of Islamic-conventional pair for Malaysia indices by using static copula and time-varying copula approach. The closing prices of Malaysia indices represented by KLCI (conventional) index and FBMHS (Islamic) index for the period of 21 May 2007 until 28 September 2018 are used as a sample data. The results show that KLCI-FBMHS pair is strongly correlated, different input models (ARMA-GARCH and ARMA-EGARCH) have identical dependence structure but slightly different value of parameter estimated, and the time-varying Gaussian copula is chosen as the best dependence model. Finding suggest that the diversification between Islamic-conventional pair is worthwhile during stable period.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.