Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지
DOI QR코드

DOI QR Code

Implementing of a Machine Learning-based College Dropout Prediction Model

머신러닝 기반 대학생 중도탈락 예측 모델 구현 방안

  • 노윤정 (동명대학교 소프트웨어학과)
  • Received : 2024.04.16
  • Accepted : 2024.06.30
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study aims to evaluate the feasibility of an early warning system for college dropout by machine learning the main patterns that affect college student dropout and to suggest ways to implement a system that can actively prevent it. For this purpose, a performance comparison experiment was conducted using five types of machine learning-based algorithms using data from the Korean Educational Longitudinal Study, 2005, conducted by the Korea Educational Development Institute. As a result of the experiment, the identification accuracy rate of students with the intention to drop out was up to 94.0% when using Random Forest, and the recall rate of students with the intention of dropping out was up to 77.0% when using Logistic Regression. It was measured. Lastly, based on the highest prediction model, we will provide counseling and management to students who are likely to drop out, and in particular, we will apply factors showing high importance by characteristic to the counseling method model. This study seeks to implement a model using IT technology to solve the career problems faced by college students, as dropout causes great costs to universities and individuals.

본 연구는 대학생의 중도탈락에 영향을 주는 주요 패턴을 기계 학습하여 대학 중도탈락에 대한 조기 경보 시스템의 타당성을 평가하고 적극적으로 예방할 수 있는 시스템의 구현 방안을 제시하고자 한다. 이를 위해 한국교육개발원에서 실시한 한국교육종단연구 2005(Korean Educational Longitudinal Study, 2005)의 데이터를 사용하여 기계학습 기반의 5종의 알고리즘을 이용하여 성능 비교 실험을 실시하였다. 실험결과, 중도탈락 의도를 가진 학생의 식별 정확률(precosion)은 랜덤 포레스트(Random Forest)를 사용할 때 최대 94.0%, 중도탈락 의도를 가진 학생의 재현율(recall)은 Logistic Regression를 사용할 때 최대 77.0%로 측정되었다. 마지막으로 가장 높은 예측 모델을 바탕으로 중도탈락 가능성이 높은 학생을 상담 관리하며 특히, 특성별로 높은 중요도를 보이는 요인을 상담법 모델에 적용하고자 한다. 본 연구는 중도탈락이 대학과 개인에게 있어 큰 비용을 초래함과 대학생들이 직면한 진로 문제를 해결하기 위해 IT 기술을 활용한 모델을 구현하고자 한다.

Keywords

Acknowledgement

이 논문은 2022학년도 동명대학교 교내학술연구비 지원에 의하여 연구되었음(2022B005)

References

  1. Korea Educational Development Institute, Korean Education Statistics Yearbook, 2023
  2. D. H. Jeong & J. Y. Park, "Data Analysis of Dropouts of College Students Using Topic Modeling", Journal of the Korea Institute of Information and Communication Engineering, vol.25, no.1, pp.88-95, 2021
  3. P. Perchinunno, M. Bilancia, & D. Vitale, "A Statistical Analysis of Factors Affecting Higher Education Dropouts", Social Indicators Research, vol.156, pp.341-362, 2021
  4. M. Kang, E. Lee & E. Lee, "Trends and influencing factors of college student's dropout intention", In Forum for Youth Culture, vol.58, pp.5-30, 2019
  5. C. Park, "Development of Prediction Model to Improve Dropout of Cyber University"Journal of the Korea Academia-Industrial Cooperation Society, vol.21, no.7, pp.380-390, 2020
  6. E. J. Lee, Y. Song, J. H. Kim & S. H. Oh, "An Exploratory Study on Determinants Predicting the Dropout Rate of 4-year Universities Using Random Forest: Focusing on the Institutional Level Factors", Journal of Educational Technology, vol.36, no.1, pp.191-219, 2020
  7. Tinto, V,"Dropout from higher education: A theoretical synthesis of recent research", Review of educational research, vol.45, no.1, pp.89-125, 1975
  8. Stinebrickner, Todd R. Stinebrickner, R,"A Major in Science? Initial Beliefs and Final Outcomes for College Major and Dropout," The Review of Economic Studies, vol.8, no.1, pp.426-472, 2014
  9. Adamopoulou, E., Tanzi, G. M, "Academic Dropout and the Great Recession," Journal of Human Capital, vol.11, no.1, pp.35-71, 2017
  10. Horstschraer, J., Sprietsma, M, "The Effects of the Introduction of the Bachelor Degree on College Enrollment and Dropout Rates", Education Economics, vol.23, no.3. 2015
  11. Sara, N. B., Halland, R., Igel, C., Alstrup, S, "High-school dropout prediction using machine learning: A danish large-scale study", In ESANN 2015 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence, pp.319-24, 2015
  12. Sansone, D, "Beyond Early Warning Indicators: High School Dropout and Machine Learning", Oxford Bulletin of Economics and Statistics, 2018
  13. Berens, J., Schneider, K., Goertz, S., Oster, S., and Burghoff, J, "Early Detection of Students at Risk-Predicting Student Dropouts Using Administrative Student Data and Machine Learning Methods", CESifo Working Paper, No.7256, 2018
  14. I. E. Isphording, T. Raabe, "Early Identification of College Dropouts Using Machine-Learning; Conceptual Considerations and an Empirical Example", Institute of Labor Economics, no.89, 2019
  15. Y. J. Roh, "Empirical analysis of factors influencing failure to drop out; Focusing on career adaptability", International Next-generation Convergence technology Association, vol.6, no.5, pp.876-889, 2022
  16. S. Y. Kim, "Analysis of the movement path structure of college dropouts", Educational Science Research, vol.43, no.3, pp.131-163, 2012
  17. S. I. Han, "Analysis of Elements of Retention Corresponding to College Dropout Factors", Korean Association For Learner-Centered Curriculum And Instruction, vol.19, no.4, pp.1239-1257, 2019
  18. D. F. Williams, "The impact of career workshops on freshman college students at risk for dropout: An action research study", Journal of College Student Retention, vo.13, no.1, pp.37-62, 2011