Exploring Secondary School Performance by Using Machine Learning Algorithms

Felicia; Ferren

doi:10.55927/jeda.v1i1.429

Authors

Felicia Universitas Pelita Harapan
Ferren Universitas Pelita Harapan

DOI:

https://doi.org/10.55927/jeda.v1i1.429

Keywords:

Education Performance, secondary education, descriptive statistics, prescriptive analytics, predictive analytics

Abstract

Education is an important factor to achieve a better life and to help the economy. There are lots of levels of education and the education level that we will analyze is secondary education. Secondary education provides lots of benefits, starting from knowledge and skills, training in attitudes, instincts, and ensuring students will get a job after graduating. Not only that, but Portuguese secondary education also guides the development of the students so they will be well prepared for work and real-life situations. The educational level of Portuguese has also improved from last decades because in the past, lots of students failed and this causing failure rates is increasing. The failures are caused by Mathematics which are the core subjects. Because of this, Portuguese schools are still monitoring students who didn’t pass yet by using the data. We will analyze using 3 operators (i.e. Generalized Linear Model , Random Forest, Naive Bayes) and found out that past grades, demographic, and several attributes play a role in education (Cortez & Silva, 2008). We also found that Naive Bayes method has a high accuracy. The goal of these projects is to identify what makes education successful and fail and to aim for any new prediction.

Downloads

Download data is not yet available.

References

Cheng, L. (2017). Exploring the Factors that Affect Secondary school’s Mathematical and Portuguese Performance in Portugal. Masters Dissertation Technological University Dublin. https://doi.org/10.21427/D7P33K

Cortez, P., & Silva, A. (2008). Using data mining to predict secondary school student performance. 15th European Concurrent Engineering Conference 2008, ECEC 2008 - 5th Future Business Technology Conference, FUBUTEC 2008, 2003(2000), 5–12.

Dey, N., Ashour, A. S., & Nguyen, G. N. (2017). Deep learning for multimedia content analysis. Mining Multimedia Documents, 1(4), 193–203. https://doi.org/10.1201/b21638

Farooq Joubish, M., Memon, G., & Ashraf Khurram, M. (2010). Impact of Parental Socio-Economic Status on Students’ Educational Achievements at Secondary Schools of District Malir, Karachi. Middle-East Journal of Scientific Research, 6(6), 678–687.

Gobena, G. A. (2018). Family Socio-economic Status Effect on Students’ Academic Achievement at College of Education and Behavioral Sciences, Haramaya University, Eastern Ethiopia. Journal of Teacher Education and Educators, 7(3), 207–222.

Louppe, G. (2014). Understanding Random Forests: From Theory to Practice. July. http://arxiv.org/abs/1407.7502

Mine, Y., Hiraishi, H., & Mizoguchi, F. (2001). Collaboration of networked home electronics using multi-agent technology. Annual Conference of the North American Fuzzy Information Processing Society - NAFIPS, 5(9), 2648–2652.

https://doi.org/10.1109/nafips.2001.943641

OCDE. (2020). Education Policy Outlook: Portugal. OECD Journals, 31. https://www.oecd.org/education/policy-outlook/country-profile-France-2020.pdf

OECD. (2006). Tertiary Education in Portugal Background Report. In Higher Education. http://dx.doi.org/10.1787/104853273381 and

Sastri, R., & Setiadi, Y. (2018). Laporan Penelitian Dosen Stis Generalized Linear Mixed Model Untuk Data Kematian Bayi Di Indonesia Generalized Linear Mixed Model. 1–17.

Thompson, C. B. (2009). Descriptive Data Analysis. Air Medical Journal, 28(2), 56–59. https://doi.org/10.1016/j.amj.2008.12.001