IJSTR

International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
0.2
2019CiteScore
 
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020

CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT

IJSTR >> Volume 10 - Issue 10, October 2021 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Application Of Machine Learning (Linear Regression Model) To Predict Students Enrollment Among Senior High Schools In Ghana

[Full Text]

 

AUTHOR(S)

Osei Wusu Brempong Jnr

 

KEYWORDS

Machine learning, simple linear regression, prediction, enrollment, GPA

 

ABSTRACT

The mission of the Ghana Education Service (GES) [1], is to ensure that all Ghanaian children of school-going age are provided with inclusive and equitable quality formal education and training through effective and efficient management of resources to make education delivery relevant to the manpower needs of the nation. The GES uses a computerized school selection and placement system that assigns senior high schools to students based on their test scores from previous Junior secondary schools. The computerized school selection and placement system (CSSPS) uses a deferred acceptance algorithm for each school assignment. Under these procedure students are ranked according to their priority levels (that is Test scores in the case of the CSSPS) [2]; they are then proposed as a match to their first-choice school in order of their test score rankings. Students are assigned to their first choice if there is a space available in the schools. What the CSSPS failed in doing is to determine the average number of students that can be allocated to each school during the placement selection process. The objective of this research is to use machine learning (linear regression) to predict the increase in student enrollment for schools in each region based on the school’s average test score performance i.e. average GPA from the previous year. Firstly, we investigate the relationship between increase in student’s applications for each school and the school average GPA (test score) from previous year. A sample dataset from 10 senior high schools in the capital region of Ghana was used for this research. Supervise machine learning models and associated algorithm (simple linear regression) to analyze data for regression helped in training the model to predict the increase in student’s enrollments for each school based on the school average GPA (test scores)

 

REFERENCES

[1] Ghana education service, GES. (2020 February 1). Enabling an effective teaching and learning environment. Ministry of education. https://ges.gov.gh/about-us/
[2] Pearl Adiza Babah, Agyemang Frimpong, Ronald Osei Mensah, Andrews Acquah .(2020). ‘Computerized School Selection and Placement System in Ghana: Challenges and The Way Forward’. European journal of education science. Vol.7 No.2 ISSN: 1857- 6036
[3] Ministry of education, MOE. (2017). changing Ghana through education. Government of Ghana. https://moe.gov.gh/free-shs-policy/#
[4] Amedahe, F.K; & Asamoah-Gyimah, E. (2005). Introduction to educational research. Cape Coast: Centre for Continuing Education of the University of Cape Coast (CCEUCC)
[5] Prakrteswar santikary, (sept 19 2019). Artificial intelligence and machine learning. ERT. https://www.ert.com/blog/artificial-intelligence-and-machine-learning-part-1-definitions-similarities-and-differences/
[6] Sanford Weisberg,” Applied Linear Regression”4THed. John Wiley & Sons,pp.21-59,2014
[7] Montgomery, D. C. and Peck, E. A “Introduction to linear regression analysis” 5th ed. Wiley. New York, pp.12-58, 2012.
[8] Barnett, V. and Lewis, T, “Outliers in Statistical Data” Wiley and son, New York, 1994.
[9] Belsley, D. A., Kuh, E. and Welsch, R. E. “Regression Diagnostics: Identifying influential data and sources of collinearity” John Wiley & Sons, New York, 1980.
[10] Chatterjee. S and Hadi. A. S. “Influential Observations, High Leverage Points, and Outliers in Linear Regression” Statistical Science, Vol. 1, No. 3, pp. 379-393, 1986