Identifying Patterns of Students Academic Performance from Tracer Evaluation using Descriptive Data Mining
Fadzilah Siraj1, Nur Azzah Abu Bakar2
1Fadzilah Siraj, School of Computing, College of Arts and Sciences, Universiti Utara Malaysia.
2Nur Azzah Abu Bakar, School of Computing, College of Arts and Sciences, Universiti Utara Malaysia.
Manuscript received on 26 June 2019 | Revised Manuscript received on 14 July 2019 | Manuscript Published on 26 July 2019 | PP: 187-191 | Volume-8 Issue-2S2 July 2019 | Retrieval Number: B10340782S219/2019©BEIESP | DOI: 10.35940/ijrte.B1034.0782S219
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The Ministry of Higher Education Malaysia has collected data through tracer study since 2007. The aim is to gather feedbacks from graduates as a basis improve to basis in improving. The availability of tracer study data in digital format offers various advantages to decision makers as many tools are available to extract and discover the hidden knowledge within the large databases. This paper presents the applicability of descriptive data mining and logistic regression to discover the hidden knowledge within the tracer study data with respect to measuring academic performance of Arts and Sciences graduates of Malaysia public universities. The impact of independent variables, i.e. Bahasa Melayu, English Language and Malaysian University English Test on the academic performance is investigated. The empirical results suggest that the academic performance between male and female graduates from Arts and Science fields is significantly different. Variables such as Bahasa Melayu, English Language and Malaysian University English Test showed a significant correlation with academic performance. The results also exhibit that the impact on academic performance of Arts graduates is different from the Science graduates. Guided by these empirical findings, this study suggests an academic performance model for Arts and Science graduates of Malaysia public universities.
Keywords: Academic Performance, Descriptive Data Mining, Logistic Regression, Tracer Study.
Scope of the Article: Data Mining