본문 바로가기 주메뉴 바로가기
22대 대한민국 국회 국회정보길라잡이 국회의원검색
회원가입 로그인
HOME

정보검색

소장정보 검색

국회도서관 홈으로 정보검색 소장정보 검색

결과 내 검색

동의어 포함

고급검색

인명/단체명

저자정보 상세정보
인명/단체명을 입력하세요.

키워드

  • 대표어

  • 외국어

-

목차보기

Title Page

Abstract

Contents

I. Introduction 9

II. Methodologies 11

2.1. Risk Information 11

2.2. Risk Information-adjusted Hierarchical Autoencoder (RI-HAE) 12

III. Experimental Results 19

3.1. Data Description 19

3.2. Data Preprocessing 19

3.3. Model Structure 21

3.4. Results Analysis 22

IV. Discussion 28

V. Conclusion 29

References 30

List of Tables

Table 1. Variable Description 21

Table 2. The number of nodes in each layer 22

Table 3. The mean values of each variable for each group 23

Table 4. Results of Bonferroni post-hoc test for each risk information 24

List of Figures

Figure 1. Overview of Vanilla AE. 13

Figure 2. Overview of RI-HAE. 14

Figure 3. Overview of preprocessing 19

초록보기

As the amount of data becomes vast, it takes a lot of time to grasp it and it is difficult to understand the context. To overcome this, the studies on composite indicators are active, which aggregate data to present comprehensive information across the various fields. However, in the financial field, indicators are defined according to the subjectivity of the researcher and utilized it to evaluate the financial status of households. Due to this situation, there are limitations that the financial status of the household is evaluated differently according to the researchers' definition and the indicator cannot consider the various factors in combination. To cope with limitations, in this paper, we propose a Risk Information-adjusted Hierarchical Autoencoder (RI-HAE), a model that presents a data-based comprehensive Household Financial Health Risk Score (HFH-RS) using household financial data. RI-HAE is a hierarchical algorithm that defines the risk information for each variable based on domain knowledge and then reduces the dimension while reflecting it to extract the HFH-RS. To evaluate the validity of HFH-RS, we examined whether the difference in risk information among the top 5%, middle 5%, and bottom 5% of HFH-RS were significant through Kruskal-Wallis and Bonferroni correction methods.

추천서가 (다양한 추천 자료를 만나보세요)

권호기사보기

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 기사목차

권호

기사명 원문보기 기사목차
닫기