VIETNAM NATIONAL UNIVERSITY, HO CHI MINH CITY : UNIVERSITY OF INFORMATION TECHNOLOGY FACULTY OF INFORMATION SYSTEMS TRAN HOANG LONG - 17521305 GRADUATION THESIS USE OF MACHINE LEARNING TO CREATE A CREDIT SCORING MODEL BACHELOR OF ENGINEERING IN | INFORMATION SYSTEMS Thesis Advisor Cao Thi Nhan, PhD HO CHi MINH CITY, 2021 VIETNAM NATIONAL UNIVERSITY, HO CHI MINH CITY : UNIVERSITY OF INFORMATION TECHNOLOGY FACULTY OF INFORMATION SYSTEMS TRAN HOANG LONG - 17521305 GRADUATION THESIS USE OF MACHINE LEARNING TO CREATE A CREDIT SCORING MODEL BACHELOR OF ENGINEERING IN | INFORMATION SYSTEMS Thesis Advisor Cao Thi Nhan, PhD HO CHi MINH CITY, 2021 ASSESSMENT COMMITTEE 1. Nguyễn Dinh Thuan — Chairman. Nguyễn Thanh Binh — Member. ACKNOWLEDGEMENTS First off, I would like to thank all the Lecturers of the University of Information Technology, especially the Members of Information Systems Faculty who provided me with helpful and valuable knowledge.
I could not have accomplished my study in this university without their whole — hearted lectures. In particular, the completion of this study could not have been possible without the expertise of Dr. Cao Thi Nhan, my beloved thesis advisor. Her kindness and enthusiasm in assisting me during the work of this thesis are extremely precious to me as well as my study.
I was so lucky to have such a wise and devoted advisor. In the making of this thesis, I tried my best to apply my domain knowledge in banking that I had the opportunity to learn, along with new technologies research to making this thesis come true. Given that I am still an undergraduate, during the implementation of this thesis, shortcomings are unavoidable. Therefore, I am looking forward to comments and suggestions to make this paper even better and earn more valuable experience from experts.
Sincerely, Tran Hoang Long UNIVERSITY OF INFORMATION TECHNOLOGY AEF Advanced Education ADVANCED PROGRAM Program IN INFORMATION SYSTEMS THESIS PROPOSAL THESIS TITLE: USE OF MACHINE LEARNING TO CREATE A CREDIT SCORING MODEL Advisor: | Dr. Cao Thi Nhan Duration: January 11", 2021 — June 26", 2021 Student: — Tran Hoàng Long — 17521305 Contents: 1. Descriptions There are more and more financial institutions joining the lending operations in Vietnam, FE Credit particularly, the leading financial institution in lending, has disbursed over 79 billion VND just in the range of February 2021 (data collected from Trusting Social). Credit growth in Vietnam is the highest in the region, rising to 18.7 per cent in 2016, 18.17 per cent in 2017 and 14 per cent in 2018, owing to a more consumer-oriented economy and a low interest rate environment.
In 2019, credit growth in Vietnam reached 12.1 per cent, which was the lowest growth rate in the previous five years. In 2020, credit growth is expected to bounce back to around 14 per cent (after adjustment to account for the covid-19 situation). Therefore, this project is to study a suitable machine learning model aimed at credit scoring that can cope with the credit growth rate in Vietnam.Scope - Dataset about accepted and rejected loans. - Classification and Regression.
Objectives - Study about the lending operations in financial institutions and how they decide whether to approve the loan or not. - Understand core concepts and algorithm using in credit scoring and credit risk model. - Learn how to train and test predictive models by using available data. - Build a credit scoring model to analyze data and display results.
Methodologies > Data analysis: perform an exploratory analysis of the data and provide summary statistics about the variables. > Feature Engineering and Selection [2]: involves data manipulation processes like transformation of categorical features, missing values treatment, infinite values handling, outlier’s detection, data leakage avoidance. > Machine Learning Models [3]: assign a score to a lead using. = Logistic regression (LR): provides binary classifications using linear relationships.
= Decision tree (DT): is constructed to assess the potential improvement using a nonlinear model. = Random Forest (RF): is deployed by averaging over a collection of decision trees. - Understand the lending operations in financial institutions. - Understand fundamental algorithms and methodologies using in credit scoring and credit risk model.
- Successfully build the credit scoring model. Timeline: Phase 1 (11/01/2021 — 15/03/2021): Study about lending operations in financial institution and their statuses. Achieve by joining one of the biggest credit scoring partners of most financial institutions and banks in Vietnam — Trusting Social. Phase 2 (16/03/2021 — 13/04/2021): Study about Machine Learning models.
Study Logistic regression, Decision tree and Random Forest, which would be used in the scope of this project. Phase 3 (14/04/2021 — 23/05/2021): Apply Machine Learning models to credit scoring. Apply Machine Learning to assign credit ratings through genetic algorithms. Phase 4 (24/05/2021 — 26/06/2021): Build a credit scoring model.
Train and test a usable scoring model with available data and display the result. Dataset: The dataset is generated by collecting accepted and rejected loans from Lending Club [1] References: [1] Lending Club, retrieved from https://www.com/investing/peer-to- peer. Machine Learning approach for Credit Scoring, August 5, 2020. [3] Bernard Dushimimana, Yvonne Wambui, Timothy Lubega and Patrick E.
Use of Machine Learning Techniques to Create a Credit Score Model for Airtime Loans, 13 August 2020. Approved by the advisor. Ho Chi Minh city, 18" Mar 2021. Signature of advisor Signature of Student Table of Contents LIST OF TABLES .cccssssessssessssesessesesscssseeseseeseneecnesseseseeseaeeseneseneseeneseeneneeneneene 10 LIST OF FIGURES .cscscsssssssssessssesesscseseeseseeseseecseseeseseeseseesenesneneseeneseeneaeeneneeee 11 LIST OF ACRONYMS AND ABBREVIATIONS.
CREDIT SCORING SYSTEM&. Credit Information Center (CIC). ST TH TH TH TT HH TH Hàn rưếg 16 1. SG nh ngư 19 CHAPTER 2.
MACHINE LEARNING MODEL FOR CREDIT SCORING 20 2. CREDIT SCORING METHODS. Expert judgements-based ImetÏOd. cà ccscscererererertrrerreveex 20 PL.
Why is credit SCOrINg ÌIHĐOFAHẨP. CREDIT SCORECARD MODEL. Logistic regression algorithm. Weight of Evidence (WOE).
k-fold cross validation. PRELIMINARY DATA EXPLORATION & SPLITTING.SẶ «1S TH HH TT HH HH TH HH 34 3. WOE FEATURE ENGINEERING AND IV CALCULATION. MODEL TRAINING AND EVALUATION.
Model selection and l€SIÏHR. vn nh nh như rưến 49 3. Calculate Credit Scores for Test Š€Í. Setting Loan Approval CHÍ-QƒŸ§.
LIST OF TABLES Table 2-1. Advantages and disadvantages of expert judgements-based method. Example of a SCOT€CATC. St 1g riey 23 Table 2-3.
IV values interpretation. ccc - Strrrey 26 Table 3-1. Reasons to drop features after preliminary data exploration. Train and Test data after pr€DTOC€SSInE.
Original confusion ImAfTIX. List of reference Caf€ØOTI€S. - nh rrey 50 Table 3-6. Final feature scorecard.
Dummy variables table of the first 5 customers in the dataset. Score calculation for the first 5 customers in the dataset. Score quality after SCOTIN .cccecee esse eeeeteeeesesesesesesesesseeeeeeeeneneaes 70 Table 3-10. Confusion matrix after applying the best threshold.
Loan status results table.cccececeeeseeeeeeeeeeseseseseseseseseseeseseeeneeneneaes 73 10 LIST OF FIGURES Figure 1. Trust Scores Websif€.- nền HH He 16 Figure 1. General Credit Decision Process Diagraim. Operation flow chart ofa P2P lender [Š].
Runtime environment technical specification. List of 18 features with more than 80% missing values. Proportion of loan_status values. train_test_split configuration code snippet.
Calculated p — values of feafUT€S. Remaining features after feature selection. Calculated WoE and IV of gradĂe. Plot of WoE by grade .- + nh riey Al Figure 3.
k — fold validation accuracy tabÌ. Parameters tuning for LightGBM. LightGBM training Fold 1’s reSuÏ. LightGBM training Fold 2’s reSuÏ.
LightGBM training Fold 3’s reSuÏ. LightGBM training Fold 4’s reSuÏ. LightGBM training Fold 5’s reSuÏ(. Mean AUC of Logistic regression on training set Figure 3.
Mean AUC of LightGBM on training set. ROC AUC, Gini index and PR AUC on test Set. PR curve plot 0010117. Transposed coefficients of features.
The score range of FICO Scores [12]. Scorecard after features scores calculafiOn. Sample score VaÏU€S.- + tt TT 111gr riey 69 Figure 3. Score distribution on total |afa.
Score, approval and rejection rates at the best threshold. 73 12 LIST OF ACRONYMS AND ABBREVIATIONS No. Acronyms Meaning 1 CIC Credit Information Center 2 WoE Weight of Evidence 3 IV Information Value 4 ANOVA Analysis of Variance 5 ROC Receiver Operating Curve 6 AUC, AUROC Area under the ROC Curve 7 PR AUC Precision-Recall AUC 8 TPR True Positive Rate 9 FNR False Negative Rate 10 FPR False Positive Rate 11 TNR True Negative Rate 12 EDA Exploratory Data Analysis 13 PD Probability of Default 14 GBDT Gradient Boosting Decision Tree 15 GOSS Gradient-based One-Side Sampling 16 EFB Exclusive Feature Bundling 13 Chapter 1. Problem definition In the process of globalization, international economic integration requires the bank system to play a big role in the economic and financial relationship.
Among many operations that banks conduct, lending and deposit are the biggest two with the highest ratio in the source of capital and total assets of banks. Despite the fact that it has always been a critical business operation, lending, simultaneously, is a damaging threat, affects to banks’ operations the most. And among all credit products that banks offer on the market, personal credit is irreplaceable, in fact, personal loans account for a big ratio in the total loan amount. In 2020, credit growth in Vietnam reached 12.1 per cent, which was the lowest growth rate in the previous five years.
In 2021, credit growth is expected to bounce back to around 14 per cent [1]. Given the fact that credit growth in Vietnam is the highest in the region, credit risk cannot be effectively controlled by credit officers anymore, at least in the traditional way they have been doing. Therefore, many credits scoring systems have been created to shorten this process. Credit scoring systems Credit rating is an important part of the consumer lending process.
It is an endeavor seen as one of the most popular fields of application for both data mining and operations research techniques. However, credit scoring systems are somehow unfamiliar to general customers, here are some considerable institutions and businesses which have built trustworthy credit scoring systems. 14 TRANG CHỦ __ GIỚITHỆU _ TÀIUỆU ‘THONG BẢO VỀ GIÁ SAN PHẨM THONG TIN TÍN DỤNG KHÁCH HÀNG. VAY 17531 230072021 CCBess chan 1,THÔNG BẢO 96 SUNG A CAPTONA .THÔNG Bho VA TẠO LẬP LẠI BẢN TINO ‘THONG BẢO VE CHAM ĐIỂM CHẤT LƯỢNG BẢO CAO TTTD CUA TGTD.
THN TH UH THANG 6 NĂM 2021 1637 | 2906/2021 .3-IÔNG BẢO THIỂN hi HORT ĐỘNG DANG KY 108 ws one “TN(GỤNG TRỰC TUYẾN ĐỔI VỚIKHÒCH HANG VAY THE NHÂN TẠIHÀ NỘI TPHCM, HAI PHÒNG NGHỆ AM BÀNẴNG,CÀN THƠ 4, THONG BẢO THIỂN Ki HORT ĐỘNG DANG KY Ti DUNG TRỰC TUYỂN ĐỔI VỚI QC» HANG VAY “THE NHÂN TA HÀ NỘIVÀTPRCM. CCANH BẢO CÁC HÌNH THỨC LỮA BAO MỚI VE THONG TIN TÍN DỤNG.NGÀN HÀNG NHÀ NƯỚC CHỦ TAL HỘI THÁO ‘6 cag cung pháo áo đợg Đ hận hon tok in hí qua sb và ng dợng “TRAD 964 THÔNG TA TN DUNG XUYEN BIEN GÓP. ‘0 Great Core wn toa ông mien ivy. CC cá bà aac ing gd See ener in is og eg tr Oo 6.
7HONG BẢO VE GI SAN Pr THONG TH TẾ, seams = DỤNG KHÁCH HÀNG var cao `:-THÔNG BẢO VE CHẩùĐiỂM CHẤT LONG BẢO Figure 1. CIC Homepage CIC is an institution of the State Bank of Vietnam (as shown in Figure 1. This institution has its functions of collecting, storing, analyzing, forecasting personal credit information in support of banks and financial institutions’ operations [2]. CIC gathers profiles from commercial banks in Viet Nam and proceed credit scoring upon those datasets.
Individuals and businesses can access its database and get credit information with an amount of fee. As a government institution, CIC is an extremely reliable source of credit information, therefore, this database is being used by many banks and financial institutions throughout Viet Nam. 15 Trust Scores Credit Score Fraud Score Credit Score Instonty Why choose us? phone ni Trusting Social’s Credit insi is the ght most iting, mì accurate altemativ personalized product offerings 'itobiliy and market the world Its battle-tested on over 100 credit portfolios forthe La share multiple markets.