Evaluating the Performance of Tree-Based Predictive Models as Programme Recommenders for University Entrants in Kenya.

  • Kibuthi J. Kabiru Karatina University, P.O. Box 1957-10101, Karatina.
  • Ratemo C. Makiya
  • Anduvare, E. M.
Keywords: Random Forest, Gradient Boosting, Python, KUCCPS, Programme Recommender.

Abstract

Enrolling for the wrong programme by university students has, to an extent, contributed to the high rates of discontinuation on academic grounds, repeat year cases, change of programme after registration, interuniversity transfers, deferments to change programme, drop out cases, suspension over exam irregularities as well as to strikes. This study focused on finding a technological solution for reducing these cases by evaluating three tree-based predictive models and recommending the most predictive model to implement as a programme recommender. Data was collected in five selected public universities in Kenya using Google Forms. The respondents were 308 translating to 308 rows of data with 36 columns. Numpy, Pandas, Matplotlib, Sklearn, Seaborn, Scipy, Plotly python analytics libraries were deployed using Jupyter Notebook for Anaconda. The cleaned and processed dataset features had categorical variables thus one-hot-encoding technique was employed. Data was split for training and testing with the random_state set to 42. Gini index criteria was implemented. The three models were evaluated on their performance from the optimally split data for training and test with a 80:20 ratio. Random Forest (RF) came out the most predictive at 99.3% followed by Gradient Boosting (XG Boost) at 90% then Decision Tree (DT) at 80.93%. The testing accuracy score for RF was 81.72%, XGBoost was at 75.72% and DT was at 76.34%. Confusion matrix criterion was implemented to evaluate the performance of the three models. The results of this study have demonstrated the high accuracy level of RF as the most predictive tree-based model for this real-world University crisis. The model is recommended for development as a system to be integrated into the KUCCPS portal. The integrated system is dubbed Programme Recommender which if launched would highly predict the best programme of study for application by university entrants.

References

AssessmentDay Ltd. Mercury House, Southwark, London, UK (2023) https://www.assessmentday.co.uk/.

Atela (2020) Relationship Between Personality Types and Career Choice Among Undergraduate Students of Maseno University, Kenya. 10.7176/JEP/11-14-14 Journal of Education and Practice. Vol 11, No 14 (2020) pp. 127-144

Ayiro, L. P. (2016) “Career Choices: Dilemmas Facing East African

Varsity Students.” The East African. https://www.theeastafrican.co.ke/tea/ea-universities-guide/career-choices-dilemmas-facing-east-african-varsity-students-1349048.

Bonenberger, M., Aikins, M., Akweongo, P. et al. (2020). The effects of health worker motivation and job satisfaction on turnover intention in Ghana: a cross-sectional study. Hum Resour Health 12, 43 (2014). https://doi.org/10.1186/1478-4491-12-43

Briemann, J. Friedman, R. Olshen & C. Stone. (1984). CART: Classification and Regression Trees, EBelmont, s CA:Wadsworth Statistical Press,

Business Today Kenya (2016,) Laikipia University reopens amid confusion over legality of courses. https://businesstoday.co.ke/laikipia-university-reopens-amid-confusion-over-legality-of-courses/

Cha G.W, Moon HJ, Kim YC. Comparison of Random Forest and Gradient Boosting Machine Models for Predicting Demolition Waste Based on Small Datasets and Categorical Variables. Int J Environ Res Public Health. 2021 Aug 12;18(16):8530. doi: 10.3390/ijerph18168530. PMID: 34444277; PMCID: PMC8392226.

Gathoni, N. J., Sirera, M. A., & Olaly, W. (2019). Effectiveness of counselling services on retention rate of undergraduate students in selected universities in Kenya. International Journal of Psychology and Counselling, 11(4), 30-38. https://academicjournals.org/journal/IJPC/article-abstract/2E29C4560734 https://doi.org/10.5897/IJPC2019.0558

Giuseppe B. (2021), University Dropout Problems and Solutions, https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3788701 Hanson, Melanie. “College Dropout Rates” EducationData.org, June 17, 2022, https://educationdata.org/college-dropout-ratespursuing.

Humanmetrics Inc (2023). This free personality test is based on Carl Jung’s and Isabel Briggs Myers’ personality type theory. https://www.humanmetrics.com/personality/test

Jun, Mj. (2021). A comparison of a gradient boosting decision tree, random forests, and artificial neural networks to model urban land use changes: the case of the Seoul metropolitan area. International Journal of Geographical Information Science. 35. 1-19. 10.1080/13658816.2021.1887490.

Kemboi, R.J., Kindiki, N.J., & Misigo, B. (2016). Relationship between Personality Types and Career Choices of Undergraduate Students: A Case of Moi University, Kenya. Journal of Education and Practice, 7, 102-112.

Kenya Vision 2030. (2022). Social Pillar. http://www.vision2030.go.ke/

Kumano, Michiko (2018). "On the Concept of Well-Being in Japan: Feeling

Shiawase as Hedonic Well-Being and Feeling Ikigai as Eudaimonic Well-Being". Applied Research in Quality of Life. 13 (2): 419–433. doi:10.1007/s11482-017-9532-9. ISSN 1871-2576. S2CID 149162906.

Lugulu J. and Katwa J. (2019). Impact of Deferments of Study by Undergraduate

Students in Public Universities: A Survey of Uasin Gishu County, Kenya. Journal of African Studies in Educational Management and Leadership. ISSN 2078-7650 Online# 2019, http://www.kaeam.or.ke

Maina, M.,W., K.(2020). Influence of Career Guidance Programmes on Change of Programme of Study among First-Year Undergraduate Students in Kenyan Universities. Journal of Education, 3(7), 28-41

Miheso, E. (2020). Determinants of students career choice in Tertiary Institutions in

Kakamega County, Kenya: a case of the Sigalagala National Polytechnic (Doctoral dissertation, University of Nairobi). Retrieved on March 10, 2020, from https:// bit.ly/3ifChvr

Nisha Arya Ahmed (2023) The Model Evaluation Tool Explained https://www.datacamp.com/tutorial/what-is-a-confusion-matrix-in-machine-learning

Ndung’u, Karanja & Obae, Rose. (2020). Effects of Career Placement by KUCCPS among

the Undergraduate Students in Public Universities in Kiambu County, Kenya. International Journal of Research and Innovation in Social Science. 04. 323-329. 10.47772/IJRISS.2020.41216.

Njoroge (2016). Examination Repeats, Semester Deferments and Dropping Out as Contributors of Attrition Rates in Private Universities in Nairobi County Kenya. International Journal of Education and Research Vol. 4 No. 3 March 2016. pp 225-240. https://www.ijern.com/journal/2016/March-2016/17.pdf

Nurmalitasari, Zalizah Awang Long, Mohammad Faizuddin Mohd Noor, "Factors Influencing Dropout Students in Higher Education", Education Research International, vol. 2023, Article ID 7704142, 13 pages, 2023. https://doi.org/10.1155/2023/7704142

Prajapati, Aanchal. (2023). The Japanese Secret to A Long and Happy Life. 4. 38-40. 10.53361/dmejc.v4i01.06.Psychometric Success (2023). The Myers-Briggs Assessment Test (2023 Guide) https://psychometric-success.com/aptitude-tests/test-types/myers-briggsRebecca et al (2016), Relationship between Personality Types and Career Choices

Russell, Lisa & Jarvis, Christine. (2019). Student Withdrawal, Retention and Their Sense of Belonging; Their Experience in Their Words. Research in Educational Administration & Leadership. 4. 494-525. 10.30828/real/2019.3.3.

Ryan, Yano & Rotich, Titus & Korir, Betty & Mutai, Kipkoech & Kosgei, Mathew & Koech, Julius & Msc, & Koech, Mr. (2019). Factors Influencing the Choice of College Among Undergraduate Students in Public Universities in Kenya A Case Study of the University of Eldoret.

Schippers, Michaéla C.; Ziegler, Niklas (2019). "Life Crafting as a Way to Find Purpose and Meaning in Life". Frontiers in Psychology. 10: 2778. doi:10.3389/fpsyg.2019.02778. ISSN 1664-1078. PMC 6923189. PMID 31920827.

Shikokoti et al (2023). Factors Influencing Rate of Completion of Undergraduate Students in Public Universities in Kenya. A Case of University of Nairobi, Faculty of Education. Journal of Education and Practice. 14. 2023. 10.7176/JEP/14-31-08.
Simplilearn (2024). Gradient Boosting Algorithm in Python with Scikit-Learn. https://www.simplilearn.com/gradient-boosting-algorithm-in-python-article

Sithole, Alec & Chiyaka, Edward & McCarthy, Peter & Mupinga, Davison & Bucklein, Brian & Kibirige, Joachim. (2017). Student Attraction, Persistence and Retention in STEM Programs: Successes and Continuing Challenges. Higher Education Studies. 7. 46. 10.5539/hes.v7n1p46.

Thumiki, V. R. R. (2019). Student Dropout from Foundation Program at Modern College of Business & Science, Sultanate of Oman. International Journal of Higher Education, 8(5), 118-133, DOI: https://doi.org/10.5430/ijhe.v8n5p118

Tomonori M. (2022). All You Need to Know about Gradient Boosting Algorithm − Part 2. Classification. https://towardsdatascience.com/all-you-need-to-know-about-gradient-boosting-algorithm-part-2-classification-d3ed8f56541e

UN DESA. 2023. The Sustainable Development Goals Report 2023: Special Edition - July 2023. New York, USA: UN DESA. © UN DESA. https://unstats.un.org/sdgs/report/2023/

Vivi E. Lu & Leah J. Teichholtz, Crimson Staff Writers (2022) (November 8, 2022) In Six-Year High, 27 Undergraduates Forced to Withdraw from Harvard in 2020-2021 Due to Honor Code Violations. https://www.thecrimson.com/article/2022/11/8/honor-council-withdrawals/

Wachira Kigotho.(2022) University deregisters thousands of inactive
students.https://www.universityworldnews.com/post.php?story=20220307125656824
Published
2024-10-25
How to Cite
Kabiru, K., Makiya, R., & M., A. (2024, October 25). Evaluating the Performance of Tree-Based Predictive Models as Programme Recommenders for University Entrants in Kenya. African Journal of Education,Science and Technology, 8(1), Pg. 311-321. https://doi.org/https://doi.org/10.2022/ajest.v8i1.1082
Section
Articles