RATIOS USING DATA MINING FOR RURAL BANKS
By
Hanna Mutia Agista 2-1751-010
MASTER‟S DEGREE in
MASTER OF INFORMATION TECHNOLOGY
FACULTY OF ENGINEERING AND INFORMATION TECHNOLOGY
SWISS GERMAN UNIVERSITY The Prominence Tower
Jalan Jalur Sutera Barat No. 15, Alam Sutera Tangerang, Banten 15143 - Indonesia
February 2019
Revision after the Thesis Defense on 24th January 2019
STATEMENT BY THE AUTHOR
I hereby declare that this submission is my own work and to the best of my knowledge, it contains no material previously published or written by another person, nor material which to a substantial extent has been accepted for the award of any other degree or diploma at any educational institution, except where due acknowledgement is made in the thesis.
Hanna Mutia Agista
Student Date
Approved by:
Dr. Eka Budiarto, S.T., M.Sc
Thesis Advisor Date
Dr. Eng Bagus Mahawan , B.Eng., M.Eng
Thesis Co-Advisor Date
Dr. Maulahikmah Galinium, S.Kom., M.Sc.
Dean Date
ABSTRACT
EARLY DETECTION OF BANK UNDER SPECIAL SURVEILLANCE STATUS THROUGH ANALYSIS OF FINANCIAL RATIOS AND BANK
SHAREHOLDERS RATIOS USING DATA MINING FOR RURAL BANKS
By
Hanna Mutia Agista
Dr. Eka Budiarto, S.T., M.Sc, Advisor
Dr. Eng Bagus Mahawan , B.Eng., M.Eng, Co-Advisor
SWISS GERMAN UNIVERSITY
This study aims to determine the effect of 8 bank financial ratios such as BOPO (operational efficiency ratio), CAR (Capital Adequacy Ratio), NPL (Non Performing Loan), ROA (Return On Assets), CR (Cash Ratio), KAP (quality of productive assets), PPAP (provision for loan losses) and LDR (Loan Deposit Ratio) and another ratio, namely Bank‟s Shareholder ratio towards bank predictions whether a rural bank will be declared as bank under special surveillance or not. Bank under special surveillance status is the bank's status before being declared as a failed bank.
Eight financial ratios and another ratio that comparing BOD and BOC to Bank's Shareholders can be obtained from quarterly rural bank‟s financial reports that have been published on the IFSA website during 2014-2017. The data in this research is approximately 1000 rural banks. The method to predict rural bank become bank under special surveillance is data mining. Before the data mining process, the 9 parameters used will be simplified into 5 parameters using the PCA (Principal Component Analysis). The PCA result shows that these 5 parameters are all the components that we need to consider because they are sufficient to explain 97% of the variance.
The new dataset formed from PCA with these 5 parameters as attributes was then analyzed with the data mining process. The data mining process was done using one
of the data mining tools called Rapidminer. Data mining method used are KNN and Naïve Bayes, both are classification method.
Keywords: data mining, cross validation, PCA, KNN, Naïve Bayes, predictions, rural banks, bank under special surveillance, bank financial ratios, BOD, BOC, Shareholder
© Copyright 2019 by Hanna Mutia Agista
All rights reserved
DEDICATION
I dedicate this research for my lovely husband (Hendy) who always supports me every single time, for my beautiful daughters (Dyna and Dyra) who always make me happy
and for my child in my womb who accompanied me everywhere to do this research.
ACKNOWLEDGEMENTS
I wish to thank all the lecturer and all my friend in Swiss German University for their support, patience and good advice.
Dr. Eka Budiarto,S.T, M.Sc, my thesis advisor who has provided guidance and advice during research activities and thesis writing.
Dr. Eng Bagus Mahawan , B.Eng., M.Eng, my thesis co advisors who gave me a good input regarding the research methodology.
I would like to thank my family for their infinity support. Without their support, I would not be able to pass my hardest moments.
I realize that the preparation of this thesis is still far from perfect. Therefore, I am glad to accept any suggestions and criticisms that can help me to improve the quality of this thesis. Finally, I hope that this thesis can provide benefits for all those who need it.
TABLE OF CONTENTS
Page
STATEMENT BY THE AUTHOR ... 2
ABSTRACT ... 3
DEDICATION ... 6
ACKNOWLEDGEMENTS ... 7
TABLE OF CONTENTS ... 8
LIST OF FIGURES ... 10
LIST OF TABLES ... 11
CHAPTER 1 - INTRODUCTION ... 12
1.1 Background ... 12
1.2 Research Problems ... 13
1.3 Research Objectives ... 13
1.4 Research Questions... 13
1.5 Hypothesis ... 14
1.6 Research Scope and Limitation ... 14
1.7 Significance of Study... 14
1.8 Thesis Structure ... 14
CHAPTER 2 - LITERATURE REVIEW ... 16
2.1 Rural Bank ... 16
2.2 Bank Under Special Surveillance ... 17
2.3 Failed Bank ... 17
2.4 IFSA‟s Rural Banks Financial Reports ... 18
2.5 Data Mining ... 20
2.6 KNN... 21
2.7 Naïve Bayes ... 22
2.8 Rapidminer ... 22
2.9 Previous Studies ... 23
CHAPTER 3 – RESEARCH METHODS ... 27
3.1 Research Methodology ... 27
3.2 Analytical Method ... 27
3.3 Evaluation Method ... 28
3.4 Validation Method ... 30
CHAPTER 4 – RESULTS AND DISCUSSIONS ... 32
4.1 Overview ... 32
4.1 Imbalance Dataset ... 33
4.2 Data Obtained ... 34
4.3 Data Analysis ... 38
4.4 Discussion ... 63
CHAPTER 5 – CONCLUSIONS AND RECCOMENDATIONS ... 67
5.1 Conclusions ... 67
5.2 Future Works ... 68
5.2 Recommendations ... 68
GLOSSARY ... 69
REFERENCES ... 72
CURRICULUM VITAE ... 74