DOI QR코드

DOI QR Code

A Study on Korean Local Governments' Operation of Participatory Budgeting System : Classification by Support Vector Machine Technique

한국 지방자치단체의 주민참여예산제도 운영에 관한 연구 - Support Vector Machine 기법을 이용한 유형 구분

  • Junhyun Han (AI-RPA Analysis Center, Fiscal Performance Management Institute) ;
  • Jaemin Ryou ;
  • Jayon Bae ;
  • Chunghyeok Im
  • 한준현 (재정성과연구원 AI-RPA분석센터) ;
  • 유재민 (연세대학교 글로벌행정학과) ;
  • 배재연 (재정성과연구원 AI-RPA분석센터) ;
  • 임충혁 (인하대학교 회계학과)
  • Received : 2024.03.07
  • Accepted : 2024.05.10
  • Published : 2024.05.31

Abstract

Korean local governments operates the participatory budgeting system autonomously. This study is to classify these entities into clusters. Among the diverse machine learning methodologies(Neural Network, Rule Induction(CN2), KNN, Decision Tree, Random Forest, Gradient Boosting, SVM, Naïve Bayes), the Support Vector Machine technique emerged as the most efficacious in the analysis of 2022 Korean municipalities data. The first cluster C1 is characterized by minimal committee activity but a substantial allocation of participatory budgeting; another cluster C3 comprises cities that exhibit a passive stance. The majority of cities falls into the final cluster C2 which is noted for its proactive engagement in. Overall, most Korean local government operates the participatory busgeting system in good shape. Only a small number of cities is less active in this system. We anticipate that analyzing time-series data from the past decade in follow-up studies will further enhance the reliability of classifying local government types regarding participatory budgeting.

한국의 주민참여예산제도는 자치단체별로 자율적으로 운영되도록 하고 있어서, 본 연구는 이들을 몇 개의 유사한 유형들로 구분하여서 각각의 특징들을 살펴보고자 한다. 본 연구는 다양한 머신 러닝 기법들을 활용하여 2022년도 기초 시(市)를 중심으로 운영유형을 분류하였다. 그 결과, 여러 머신 러닝 기법(Neural Network, Rule Induction(CN2), KNN, Decision Tree, Random Forest, Gradient Boosting, SVM, Naïve Bayes) 중에서 SVM 기법이 성능이 가장 좋은 것으로 확인되었다. SVM 기법이 밝혀낸 운영유형은 모두 3개인데, 하나는 위원회 활동은 적게 하지만, 참여예산은 많이 확보하는 클러스터(C1)이고, 다른 하나는 주민참여예산제에 매우 소극적인 도시들의 클러스터(C3)이다. 마지막 클러스터(C2)는 참여예산에 전반적으로 적극적인데, 대다수 지역이 여기에 해당한다. 결론적으로 한국의 대다수 자치단체는 주민참여예산제를 긍정적으로 운영하고 있으며, 오직 소수의 자치단체만 소극적이다. 후속 연구로 지난 10여 년간의 시계열 자료를 분석한다면, 우리는 주민참여예산에 관한 지방자치단체 유형 분류의 신뢰도를 더욱 높일 수 있을 것으로 기대한다.

Keywords

References

  1. Ministry of the Interior and Safety. "Operation Manual of Citizen Participation Budgeting System," 2023.
  2. C. H. Jung, I. J. Kang, D. J. Bae & S. Y. Lee, "Improvement of Management Plan for Citizen Participation Budget System," Final Report. Ministry of the Interior and Safety. 2022.
  3. Y. S. Kim & S. M. Jeon. "A Study on the System Improvement for the Activation of Citizen Participatory Budgeting: Focused on the Case of Metropolitan Cities," The Korea Local Administration Review, Vol. 37, No. 2. pp. 67-110, 2023. DOI : 10.22783/krila.2023.37.2.067
  4. C. J. Kwack, "Designing Participatory Budgeting Model and Its Operational System for Local Government," Korean Journal of Local Finance, Vol. 10, No. 1, pp. 247-276, 2005.
  5. M. G. Park, "A Study on the Citizen Participatory Budget Decision-making Process in Seoul : Focusing on Analysis of Influential Factors and Performance by Autonomous Districts," doctoral dissertation, Graduate School, University of Seoul, 2022.
  6. J. J. Chung, "A Study on Improvement Plan of the Citizen Participatory Budgeting in each Province : Focused on Gyeonggi Province Case," The Korea Local Administration, Vol. 34, No. 2, pp. 101-134, 2020. DOI : 10.22783/krila.2020.34.2.101
  7. G. Y. Lee & C. L. Cho, "Participatory Budget System and Local Government Corruption," Journal of Local Government Studies, Vol. 33, No. 3, 2021. DOI : 10.21026/jlgs.2021.33.3.97
  8. D. U. Shin, H. J. Yeom & S. S. Park, "Low-cost Prosthetic Hand Model using Machine Learning and 3D Printing," The Journal of the Convergence on Culture Technology (JCCT), Vol. 10, No. 1, pp. 19-23, January 2023, http://dx.doi.org/10.17703/JCCT.2024.10.1.19
  9. E. M. Lee & J. H. Lee. "Privacy-Preserving Credit Scoring via Support Vector Machine Training with Homomorphic Encryption," J ournal of the Korea Institute of Information and Communication Engineering (JKIICE), Vol. 27, No. 9, pp. 1140-1145, September 2023. DOI : 10.6109/jkiice.2023.27.9.1140