Student Academic Streaming Using Clustering Technique

Abstract

The balance of human capital supply and industry demands are crucial to sustain a competitive advantage in order to ensure stability of economic growth. Unfortunately, companies often find it hard to recruit the right people. Many ideas obviously relate to connect human capital to education because human capital is created through education. In the education sector, there is a critical need to develop an effective planning mechanism to distribute the students into the most suitable area in the industry. In order to achieve this, the student's pathway needs to be planned systematically in school by identifying the student's streaming based on their academic performance. In this case, students who have the same performance will be grouped in the same cluster using a data mining technique. However, the problem is that, it is difficult to identify real potential for the students, because their performance is not well monitored, and current assessment systems do not support the student's academic planning activities. Besides, there is no specific technique used to group students into clusters based on their performance. This study aims to overcome the problem by grouping the students according to their performance using clustering techniques and to propose a suitable model. This study aims to overcome the problem by identifying a suitable clustering model that can be used to analysis an educational data. The data involves is student performance data. Based on the data, two clusters of students are created which is science and arts. A novelty in the method of study is the use of three clustering models and a comparison among them in order to find a suitable clustering model to be used with student academic performance data. The study was conducted in five schools in Malaysia to support students' grouping in two different academic streams, which are science and art. The result demonstrated the best model of clustering technique that is suitable for mining the educational data. Moreover, suitable streaming based on the students' performance and education policy was created from the results. It can be used to assist schools and students in determining the appropriate streaming for the students, and support for the human capital needs by the country in the future.

Machine Learning for Enhanced Classroom Homogeneity in Primary Education

“…Internationally, research in Malaysia has aimed to identify suitable clustering models for the analysis of educational data. The goal is to align student academic pathways with national interests and to refine educational strategies based on student performance data (Salwana et al, 2017). This research highlights the intricate relationship between classroom composition, educational strategies, and academic outcomes, emphasizing the significance of a nuanced approach to student grouping and instructional design in meeting educational goals.…”

Big Data Technology-Enabled Analytical Solution for Quality Assessment of Higher Education Systems

“…The value of QS for a SPHE student with a known university rank is calculated by performing linear scaling. The formula used for linear scaling 2 are given in equations (1), (2) and (3).…”

“…The derivation of the formula for QS calculation in this scenario is given below. The value of variables used in equations (1), (2) and 3 A description of the variables used in the described formula is given in Table IV. Placement data like company ranking and package offered can be cumulatively used as base data for the students who opt for campus placed jobs. The company rankings can be taken from survey results of credible private agencies like Economic Times 3 , which have created surveys with the objective to create top recruiters list.…”

“…In order to accommodate this case, the value of is calculated on a scale of 1 to 5. The value of can be calculated using the equations (1), (2) and 3 Scaling of package offered to students opting for campusplaced jobs on a scale of 1 to 5 also requires linear scaling. Therefore, equations (1), (2) and 3are used with the following parameters: Quality score for SOFJ ( ) is determined using the following equation:…”

“…This data is high in volume, contains images and textual data for variety and is generated on a yearly basis. Moreover, the use of data mining and machine learning in educational analytics [2] makes big data technologies a relevant solution for educational analytics [3]. When projected in the global domain, education data is certainly a ‗big' data set.…”