DOI QR코드

DOI QR Code

A Study on Management of Student Retention Rate Using Association Rule Mining

연관관계 규칙을 이용한 학생 유지율 관리 방안 연구

  • 김종만 (제주대학교 경영정보학과) ;
  • 이동철 (제주대학교 경영정보학과)
  • Received : 2018.10.17
  • Accepted : 2018.12.04
  • Published : 2018.12.31

Abstract

Currently, there are many problems due to the decline in school-age population. Moreover, Korea has the largest number of universities compared to the population, and the university enrollment rate is also the highest in the world. As a result, the minimum student retention rate required for the survival of each university is becoming increasingly important. The purpose of this study was to examine the effects of reducing the number of graduates of education and the social climate that prioritizes employment. And to determine what the basic direction is for students to manage the student retention rate, which can be maintained from admission to graduation, to determine the optimal input variables, Based on the input parameters, we will make associative analysis using apriori algorithm to collect training data that is most suitable for maintenance rate management and make base data for development of the most efficient Deep Learning module based on it. The accuracy of Deep Learning was 75%, which is a measure of graduation using decision trees. In decision tree, factors that determine whether to graduate are graduated from general high school and students who are female and high in residence in urban area have high probability of graduation. As a result, the Deep Learning module developed rather than the decision tree was identified as a model for evaluating the graduation of students more efficiently.

최근 학령인구 감소에 따라 많은 문제점들이 나타나고 있다. 우리나라는 인구대비 가장 많은 대학을 보유하고 있기 때문에 각 대학의 생존에 필요한 최소한의 학생 유지율 관리가 점점 더 중요해 지고 있다. 따라서 본 연구는 계속되는 학력인구의 감소에 따라 각 대학들이 생존 방안으로 학생 유지율의 적절한 관리 방안을 모색한다. 이를 위하여 특정 대학에 입학한 학생들을 대상으로 성별, 출신고, 출신지역, 성적, 졸업여부 등의 데이타를 분석하여, 학생들이 입학에서 졸업에 이르기까지 지속적으로 유지될 수 있는 학생 유지율을 관리하기 위한 기본적인 방향이 어떤 것인지 알아본다. 또한, 최적의 입력 변수를 파악하고, 최적의 입력 파라메터를 기초로 apriori 알고리즘을 이용하여 연관 분석을 실행하여 유지율 관리에 가장 적합한 자료를 수집할 수 있도록 한다. 이를 바탕으로 각 대학들이 학생들을 모집하고 유지하는데 도움이 되도록 가장 효율이 높은 딥러닝(Deep Learning) 모듈을 개발하기 위한 기초 자료로 만들고자 한다. 의사결정트리를 활용하여 졸업여부를 측정한 결과는 딥러닝의 정확도 보다 낮은 75%로 나타났다. 의사결정트리에서 졸업여부를 결정하는 요인은 일반고를 졸업하고, 도시지역에 거주하면서 여성이면서 성적이 높은 학생들이 졸업확율이 높은 것으로 나타났으며 결과적으로 의사결정트리 보다는 개발된 딥러닝듈이 더 효율적으로 학생들의 졸업여부를 평가할 수 있는 모델로 나타났다.

Keywords

SOJBB3_2018_v23n6_67_f0001.png 이미지

Fig. 1 How to utilize data

SOJBB3_2018_v23n6_67_f0002.png 이미지

Fig. 2 Using Training Data, Testing Data

SOJBB3_2018_v23n6_67_f0003.png 이미지

Fig. 3 Nueral Network(NN)

SOJBB3_2018_v23n6_67_f0004.png 이미지

Fig. 4 Accuracy when Configuring 5 Hidden Layers

SOJBB3_2018_v23n6_67_f0005.png 이미지

Fig. 5 Deep Learning Accuracy

SOJBB3_2018_v23n6_67_f0006.png 이미지

Fig. 6 Cost Change Status

SOJBB3_2018_v23n6_67_f0007.png 이미지

Fig. 7 Comparison of Accuracy Difference according to Hidden Layer Configuration (Layer 3, Layer 5)

Table 1 Composition of Data

SOJBB3_2018_v23n6_67_t0001.png 이미지

Table 2 Main Characteristics of Data

SOJBB3_2018_v23n6_67_t0002.png 이미지

Table 3 Top 10 Items with 10% Frequency of Use and Support of Data

SOJBB3_2018_v23n6_67_t0003.png 이미지

Table 4 Analysis Result Summary

SOJBB3_2018_v23n6_67_t0004.png 이미지

Table 5 Measure Accuracy Using Decision Tree Model

SOJBB3_2018_v23n6_67_t0005.png 이미지

Table 6 Decision Tree and Deep Learing Prediction Accuracy Comparison

SOJBB3_2018_v23n6_67_t0006.png 이미지

References

  1. Kim, S. S., "A Exploratory Study on Withdrawal and Transfer of Korean College Students: The Influence of College-Choice Reason and Satisfaction Afterwards," The Journal of Korean Education, Vol. 35, No. 1, pp. 227-249, 2008.
  2. Kim, J. M., " Study on Prevention of Student Drop out Rate Using Deep Learning," Jeju National University, KOREA, 2017.
  3. Bang, E. H. and Others 7, "Effect of Korean High School Student's Mental Health on Academic Achievement and School Dropout Rate," J Korean Acad Child Adolesc Psychiatry, Vol. 27, No. 3, pp. 173-180, 2016. https://doi.org/10.5765/jkacap.2016.27.3.173
  4. Lee, H. J. and Kim, Y. N., "The School Related Factors Affecting High School Dropout Rates," Asian Journal of Education Vol. 13, No. 1, pp. 149-185, 2012. https://doi.org/10.15753/aje.2012.13.1.007
  5. Sim, H., "A Grounded Theory-Based Analysis on the Factors that Causing Dropout of Students in Korean National Universities," Journal of Education and Culture, Vol. 23, No. 2, pp. 105-128, 2017. https://doi.org/10.24159/joec.2017.23.2.105
  6. Lee, H. J., "Individual, Family, School and Community Related Variables Predicting Longitudinal School Adjustment in Urban Adolescents," Journal of Education and Culture, Vol. 21, No. 2, pp. 27-56, 2015.
  7. Cho, Y. J. and Han, S. G., "An Analysis of Student and Parent Factors Influencing School Adjustment," The Education Assignment Institute of Chonbuk National University, KOREA, pp. 117-144, 2015.
  8. Lee, B. H. and Kang, D. K., "A Study of School Maladjustment Action Factors in Secondary School Students," Journal of Education and Culture, Vol. 20, No. 3, pp. 125-148, 2014. https://doi.org/10.24159/joec.2014.20.3.125
  9. Lee, J. H. and Lee, H. K., "A Study on Unstructured Text Mining Algorithm through R Programming Based on Data Dictionary," Journal of the Korea Industrial Information Systems Research, Vol. 20, No. 2, pp. 113-123, 2015. https://doi.org/10.9723/jksiis.2015.20.2.113
  10. Lee, Y. H. and Jeon, H. J., "Students' Information Communication Skill Affecting Relationship among Technology Acceptance, Education Service Quality, Relationship Quality, and Education Service Satisfaction," Journal of the Korea Industrial Information Systems Research, Vol. 16, No. 5, pp. 73-81, 2011. https://doi.org/10.9723/jksiis.2011.16.5.073
  11. Lee H. G. and Shin, Y. H., "Protein Disorder/Order Region Classification Using EPs-TFP Mining Method," Journal of the Korea Industrial Information Systems Research, Vol. 17, No. 6, pp. 59-72, 2012. https://doi.org/10.9723/jksiis.2012.17.6.059