Model Peramalan Bilangan Calon Tarik Diri dari Peperiksaan Awam Malaysia Menerusi Pendekatan Perlombongan Data dan Petua
Non-Attendance Candidates’ Prediction Model for Malaysia Public Exam Using Data Mining and Rules Approach
DOI:
https://doi.org/10.37134/jictie.vol8.1.3.2021Keywords:
perlombongan data, peramalan, model, petua, CRISP-DMAbstract
Abstrak
Peningkatan jumlah data tersimpan tentang hal akademik pelajar bermula dari tahap sekolah rendah, sekolah menengah, kolej hingga universiti telah dibantu dengan perkembangan teknologi storan data. Data yang pelbagai ini wajar diekstrak ke dalam pengetahuan yang membantu dalam pembuatan keputusan dari pelbagai peringkat. Isu calon yang tidak hadir peperiksaan umum adalah masalah berkala dan memberi kesan kepada usaha mengoptimumkan kos pengurusan dalam era perbelanjaan berhemah. Sebanyak 15 peratus hingga 30 peratus calon tidak hadir peperiksaan awam berdasarkan analisis ke atas data untuk sepuluh tahun dari 2007 hingga 2016. Memandangkan masalah ini wujud saban tahun, kajian ini mencadangkan penyelesaian menggunakan perlombongan data bagi membangunkan model untuk meramal calon yang berpotensi tidak hadir peperiksaan awam (Sijil Tinggi Agama Malaysia @ STAM). Pendekatan yang dicadang terdiri dari enam langkah; bermula dari pemahaman bisnes, pemahaman data, penyediaan data, permodelan, penilaian dan pengerahan. Keputusan mendapati gred yang diperoleh untuk subjek Bahasa Inggeris, Matematik dan Sains dalam keputusan peperiksaan awam tingkatan lima iaitu Sijil Pelajaran Malaysia adalah faktor utama bagi menarik diri daripada peperiksaan STAM untuk seseorang calon. Faktor ini seterusnya diwakili dalam bentuk model berasaskan petua. Penilaian ke atas model membuktikan bahawa model berpotensi untuk meramal bilangan calon yang mungkin tidak hadir peperiksaan. Ramalan ini telah disimulasi dan didapati boleh menjimatkan 10 peratus dari kos percetakan kertas soalan dan buku jawapan untuk peperiksaan STAM. Hasil kajian ini boleh dimanfaat oleh Lembaga Peperiksaan dengan membuat unjuran perbelanjaan setiap tahun bagi operasi peperiksaan dengan menggunakan model ramalan bilangan calon tarik diri. Manakala, pihak sekolah dan ibu bapa boleh memanfaatkan kajian ini untuk mencari kaedah bagi menambah baik pencapaian akademik pelajar.
Abstract
Advances in data storage technology have spurred growth in stored data on students’ academic for primary, secondary, college, and university levels. The Education Ministry could extract the rich data into knowledge to aid decision making at different levels. The issue of candidates who did not attend public exams is a recurrent problem and affects the efforts to optimize management cost in the era of prudent spending. Around 15 percent to 30 percent candidates did not attend the public exam based on a ten-year analysis from 2007 until 2016. Since the problem recurs yearly, this research proposes a solution based on data mining to develop a model that predicts candidate who has a high potential of not attending a public examination exam (i.e. Sijil Tinggi Agama Malaysia @ STAM). The proposed approach has six steps; business understanding, data understanding, data preparation, modelling, evaluation, and deployment. The results discovered that the grades obtained for English, Mathematics and Science in the public examination taken in Form 5 (Sijil Pelajaran Malaysia) are the main factors for the non-attendance of a candidate for the STAM examination. The research then implemented a rule-based model based on these factors. Model evaluation proves that the model can predict the number of candidates that may not attend the examination. The prediction has been simulated and can save up to 10 percent of the printing cost for exam papers and answer books for the STAM examination. These results can benefit Lembaga Peperiksaan by projecting the yearly expenditure for exam operations using the non-attendance candidates’ prediction model. Additionally, the school and parent may use this research to improve the students' academic performance.
Keywords: data mining, prediction, model, rules, CRISP-DM.
Downloads
References
Abu Saa, A. (2016). Educational Data Mining & Students’ Performance Prediction. International Journal of Advanced Computer Science and Applications, 7(5), 212–220. https://doi.org/10.14569/IJACSA.2016.070531
Ahmad, W. D., & Abu Bakar, A. (2018). Classification Models for Higher Learning Scholarship Award Decisions. Asia-Pacific Journal of Information Technology & Multimedia, 7(2). Penerbit Universiti Kebangsaan Malaysia (UKM Press), Dec. 2018, pp. 131–145. Crossref. https://doi.org/10.17576/apjitm-2018-0702-10.
Asif, R., Merceron, A., Ali, S. A., & Haider, N. G. (2017). Analyzing undergraduate students’ performance using educational data mining. Computers and Education, 113, 177–194. https://doi.org/10.1016/j.compedu.2017.05.007
Aydoğdu, Ş. (2020). Educational Data Mining Studies in Turkey: A Systematic Review. Turkish Online Journal of Distance Education, 21(3), 170-185. https://doi.org/10.17718/tojde.762046
Buniyamin, N., Mat, U. Bin, & Arshad, P. M. (2016). Educational data mining for prediction and classification of engineering students’ achievement. In proceedings of the IEEE 7th International Conference on Engineering Education, ICEED 2015, 49–53. https://doi.org/10.1109/ICEED.2015.7451491
Costa, E. B., Fonseca, B., Santana, M. A., de Araújo, F. F., & Rego, J. (2017). Evaluating the effectiveness of educational data mining techniques for early prediction of students’ academic failure in introductory programming courses. Computers in Human Behavior, 73, 247–256. https://doi.org/10.1016/j.chb.2017.01.047
Dutt, A., Ismail, M. A., & Herawan, T. (2017). A Systematic Review on Educational Data Mining. IEEE Access, 5, 15991-16005. https://doi.org/10.1109/ACCESS.2017.2654247
Fischer, C., Pardos, Z. A., Baker, R. S., Williams, J. J., Smyth, P., Yu, R., Slater, S., Baker, R., & Warschauer, M. (2020). Mining Big Data in Education: Affordances and Challenges. Review of Research in Education, 44(1), 130–160. https://doi.org/10.3102/0091732X20903304
Ismail, L., Materwala H., & Hennebelle A. (2021) Comparative Analysis of Machine Learning Models for Students’ Performance Prediction. In: Antipova T. (eds) Advances in Digital Science. ICADS 2021. Advances in Intelligent Systems and Computing, 1352. Springer, Cham. https://doi.org/10.1007/978-3-030-71782-7_14
Koedinger, K.R., D'Mello, S., McLaughlin, E.A., Pardos, Z.A., & Rosé, C.P. (2015), Data mining and education. WIREs Cogn Sci, 6, 333-353. https://doi.org/10.1002/wcs.1350
Makhtar, M., Nawang, H., Nor, S., & Shamsuddin, W. A. N. (2017). Analysis on Students Performance Using Naïve Bayes Classifier. Journal of Theoretical and Applied Information Technology, 95(16), 3993-4000.
Marbouti, F., Diefes-dux, H. A., & Madhavan, K. (2016). Computers & Education Models for Early Prediction of At-risk Students. In: A Course Using Standards-based Grading. Computers & Education, 103, 1–15. https://doi.org/10.1016/j.compedu.2016.09.005
Márquez-Vera, C., Cano, A., Romero, C., Noaman, A. Y. M., Mousa Fardoun, H., & Ventura, S. (2016). Early dropout prediction using data mining: A case study with high school students. Expert Systems, 33(1), 107–124. https://doi.org/10.1111/exsy.12135
Martínez-Plumed, F., Contreras-Ochando, L., Ferri, C., Hernandez-Orallo, J., Kull, M., Lachiche, N. J. A. H., Ramírez-Quintana, M. J., & Flach, P. A. (2019). CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories. IEEE Transactions on Knowledge and Data Engineering. https://doi.org/10.1109/TKDE.2019.2962680
Saniron, S., & Ali Othman, Z. (2019). Model Penempatan Guru Berasaskan Perlombongan Data. Journal of ICT in Education, 3, 13-23. https://ejournal.upsi.edu.my/index.php/JICTIE/article/view/2605.
Uswatun Khasanah, A., & Harwati, (2017). A Comparative Study to Predict Student’s Performance Using Educational Data Mining Techniques. Materials Science and Engineering Conference Series, 215(1), 12036. https://doi.org/10.1088/1757-899X/215/1/012036.
Zainudin, S., & Ab Aziz, M. A. (2015). Perlombongan data bagi meramal prestasi akademik pelajar. Inovasi pengajaran dan pembelajaran dalam teknologi maklumat. Pusat Pengajaran dan Teknologi Pembelajaran, UKM.
