SlideShare a Scribd company logo
1 of 53
Chapter 5
Consumer Lending
The Presentation Slides for Teaching Regulatory Technology
Website : https://sites.google.com/site/quanrisk
E-mail : quanrisk@gmail.com
Copyright © 2021 Dr. LAM Yat-fai
Declaration
 Copyright © 2021 Dr. LAM Yat-fai
 All rights reserved. No part of this presentation file may be
reproduced, in any form or by any means, without written
permission from Dr. LAM Yat-fai.
 Authored by Dr. LAM Yat-fai (林日辉),
Chief Data Scientist, CapitaLogic Limited,
Adjunct Professor of Finance, City University of Hong Kong,
Doctor of Business Administration,
CFA, CAIA, CAMS, CFE, FRM, PRM, MCSE, MCNE.
Copyright © 2021 Dr. LAM Yat-fai 2
Outline
 Sample data set
 Regulatory requirements
 Model development
 Default prediction model
 Overdue prediction model
Copyright © 2021 Dr. LAM Yat-fai 3
Two class sampling techniques
 For machine learning theories
 50% to 50%
 Real full data set
 30% to 70%
 20% to 80%
 Under sampling
 Reduce the majority class to match the minority class
 Over sampling
 Increase the minority class to match the majority class
Copyright © 2021 Dr. LAM Yat-fai 4
Full data set
Copyright © 2021 Dr. LAM Yat-fai 5
Under sampling
Copyright © 2021 Dr. LAM Yat-fai 6
Over sampling
Copyright © 2021 Dr. LAM Yat-fai 7
SMOTE
 Synthetic Minority Oversampling Technique
 Create new records from existing minority
class
 For each record of minority class
 Substitute the value of a feature with the value of a
record nearby
Copyright © 2021 Dr. LAM Yat-fai 8
Feature type
 Numeric
 Continuous feature Annual income
 Discrete feature No. of children
 Non-numeric
 Binary feature Gender
 Categorical feature Education
Copyright © 2021 Dr. LAM Yat-fai 9
Binary feature
 Gender
 Male 0
 Female 1
 Martial status
 Single 0
 Married 1
Copyright © 2021 Dr. LAM Yat-fai 10
Categorical feature
 Education
 Postgraduate
 Undergraduate
 Secondary school
 Primary school
 No education
 Country
 United States
 United Kingdom
 Canada
 Australia
 China
Copyright © 2021 Dr. LAM Yat-fai 11
Assign ranks to categorical variable
Country Label average Rank
Australia 0.21 5
Canada 0.63 1
China 0.49 3
United Kingdom 0.38 4
United States 0.52 2
Copyright © 2021 Dr. LAM Yat-fai 12
Chapter 5a2 – Sample data set (1)
 Datasets
 Chapter 5a1 – Full data set.csv
 Chapter 5a3 – Country rank
 SMOTE
 Label column y
 SMOTE percentage 58
 Edit Metadata
 Column Gender, Country
Copyright © 2021 Dr. LAM Yat-fai 13
Chapter 5a2 – Sample data set (2)
 Convert to Indicator Values
 Categorical columns Gender
 Join Data
 Join key columns for Left Country
 Join key columns for Right Country
 Select Columns in Dataset
 All columns exclude Gender, Gender-Male,
Country, Country(2)
 Convert to CSV
Copyright © 2021 Dr. LAM Yat-fai 14
Outline
 Sample data set
 Regulatory requirements
 Model development
 Default prediction model
 Overdue prediction model
Copyright © 2021 Dr. LAM Yat-fai 15
Banking activities
Deposits
< 1%
Shareholders’
equity
Dividend +
equity price
appreciation
3% - 20%
Term loans,
credit cards,
mortgages
Bank
Copyright © 2021 Dr. LAM Yat-fai 16
Major retail lending products
 Term loan
 Fixed loan principal
 No collateral
 Credit card
 Subject to a credit limit
 No collateral
 Residential mortgage
 Principal amortization
 Property as collateral
Copyright © 2021 Dr. LAM Yat-fai 17
HKMA SPM CR-G-1
General Principles of Credit Risk Management
 4.1.4 Credit decisions should be supported by
adequate evaluation of the borrower's
repayment ability based on reliable
information. Sufficient and up-to-date
information should continue to be available to
enable effective monitoring of the account.
Copyright © 2021 Dr. LAM Yat-fai 18
Commercial Banks Law, PRC
 Article 35. Before granting a loan,
commercial banks shall strictly examine the
borrower's purpose for the loan, ability to
repay the loan, method of repayment, etc.
.
Copyright © 2021 Dr. LAM Yat-fai 19
20
Default
 Generic definition
 A borrower fails to pay to the lender the interest
and/or principal in full on schedule
 Regulatory definition
 A borrower fails to pay to the lender the interest
and/or principal within 90 days of the due date
21
Survival → overdue → default
Survival
Overdue
Default
Payment
Payment
Yes
Yes No
No
90
days
Risk management objectives
 To predict whether a borrower will default in
the following one year
 Good, bad
 Good, moderate, bad
 Good, good to moderate, moderate to bad, bad
 Probability of default
Copyright © 2021 Dr. LAM Yat-fai 22
Regulatory and legal constraints
 Interpretability
 The relationship between the label and features can
be well established by experience and theory
 No violation with common sense unless the
common sense is inapplicable
 Equal opportunity
 Religion, race, disability … cannot be used
directly as a feature, as mandated by anti-
discrimination law
Copyright © 2021 Dr. LAM Yat-fai 23
Outline
 Sample data set
 Regulatory requirements
 Model development
 Default prediction model
 Overdue prediction model
Copyright © 2021 Dr. LAM Yat-fai 24
Standard procedure (1)
 Analyze regulatory requirements
 Collect historical records
 Prepare sample data set
 Over sampling
 Convert binary features into [0,1]
 Convert categorical features into ranks
Copyright © 2021 Dr. LAM Yat-fai 25
Standard procedure (2)
 Assess monotonicity and principal components
 Develop machine learning model
 Evaluate model performance
 Create prediction model
 Assess sample, positive class and negative
class accuracies
 Conduct prediction
Copyright © 2021 Dr. LAM Yat-fai 26
Modelling assumptions
 Many historical borrower records
 Many borrowers survive in one year
 Some borrowers default in one year
 There is a monotonic relationship between
 Label: whether a borrower defaults in one year
 Features: borrower information collected one year
ago
Copyright © 2021 Dr. LAM Yat-fai 27
Label
 0
 The borrower survives in one year
 1
 The borrower defaults in one year
Copyright © 2021 Dr. LAM Yat-fai 28
Features
 From application form
 Personal data
 Employment data
 Income data
 Asset data
 Liability data
Copyright © 2021 Dr. LAM Yat-fai 29
Expected monotonicity
 Strong
 Annual income, outstanding loan, equity investments
 To be verified by data
 Weak or unknown
 Education, gender, martial status
 To be determined by data
 No
 ID card no., telephone no., application date
 To be ignored
Copyright © 2021 Dr. LAM Yat-fai 30
Data dictionary
 Label
 Survive (0) or Default (1)
 Description
 The default status of a borrower in one year after
his features were collected
 Label type
 Binary
Copyright © 2021 Dr. LAM Yat-fai 31
Data dictionary
 Feature
 Income
 Description
 The total income during the last 12 month, including
fixed salary, commission and bonus, after income tax
and pension contribution have been deducted
 Feature type
 Continuous value
 Expected impact to default
 Strong
 Negative
Copyright © 2021 Dr. LAM Yat-fai 32
Data dictionary
 Feature
 Loan amount
 Description
 The outstanding loan amount
 Feature type
 Continuous value
 Expected impact to default
 Strong
 Positive
Copyright © 2021 Dr. LAM Yat-fai 33
Outline
 Sample data set
 Regulatory requirements
 Model development
 Default prediction model
 Overdue prediction model
Copyright © 2021 Dr. LAM Yat-fai 34
Two class PD model
 
       
1 2 3 N
Default Default Default Default
1 2 3 U
Survive Survive Survive Survive
1 2 3 V
PD = F x , x ,x , , x
Maximize
L = PD × PD × PD × × PD ×
1 - PD × 1 - PD × 1 - PD × × 1 - PD
35
Copyright © 2020 CapitaLogic Limited
Full data set
 Feature
 Data on existing mortgage borrowers one year ago
 Label
 Either survives or defaults in one year
 Several thousand records
 Imbalanced
 Some features missed
 Some records duplicated
Copyright © 2021 Dr. LAM Yat-fai 36
Label and all features
 Label
 0: Survives in the last year
 1: Defaults in the last year
 Loan amount
 Loan purpose
 Debt consolidation
 Home improvement
 Job title
 No. of years at current job
 No. of major derogatory reports
 No. of delinquent credit lines
 Age of oldest credit line in
months
 No. of credit enquiries in the
most recent 30 days
 No. of credit lines
 Debt-to-income ratio
Copyright © 2021 Dr. LAM Yat-fai 37
Chapter 5b2 – Sample data set (1)
 Datasets
 Chapter 5b1 – Full data set.csv
 Chapter 5b3 – Job title rank
 SMOTE
 Label column Default
 SMOTE percentage 57
 Edit Metadata
 Column Loan purpose, Job title
Copyright © 2021 Dr. LAM Yat-fai 38
Chapter 5B2 – Sample data set (2)
 Convert to Indicator Values
 Categorical columns Loan purpose
 Join Data
 Join key columns for Left Job title
 Join key columns for Right Job title
 Save as Dataset
 Select Columns in Dataset
 All columns exclude Loan purpose, Loan purpose-
Loan Consolidation, Job title, Job title(2)
 Convert to CSV
Copyright © 2021 Dr. LAM Yat-fai 39
Feature selection
 Weak monotonicity
 Mortgage amount
 No. of credit lines
 Loan purpose-Home
 No. of principal components
 8
Copyright © 2021 Dr. LAM Yat-fai 40
Chapter 5b4 – Prediction model
 Datasets
 Chapter 5b2 – Sample data set
 Chapter 5b3 – Job title rank
 Edit Metadata
 Column Job title
 Join Data
 Join key columns for Left Job title
 Join key columns for Right Job title
 Select Columns in Dataset
 All columns exclude Loan purpose, Job title, Job
title(2)
Copyright © 2021 Dr. LAM Yat-fai 41
Other standard procedures
 Run training experiment
 Create predictive experiment
 Modify Web service input and Web service output
 Run predictive experiment
 Deploy web service
 Download Excel prediction model
 Upload Excel prediction model to OneDrive
 Conduct assessment and prediction
Copyright © 2021 Dr. LAM Yat-fai 42
Excel prediction model
 5 samples test
 All samples accuracy
 Overall accuracy
 Survive class accuracy, full data set
 Upper cutoff score
 Defaulted class accuracy, full data set
 Lower cutoff score
 Prediction
Copyright © 2021 Dr. LAM Yat-fai 43
Outline
 Sample data set
 Regulatory requirements
 Model development
 Default prediction model
 Overdue prediction model
Copyright © 2021 Dr. LAM Yat-fai 44
Label and all features, three class
 Label
 Survive
 Overdue
 Default
 Loan amount
 Loan purpose
 Debt consolidation
 Home improvement
 Job title
 No. of years at current job
 No. of major derogatory reports
 No. of delinquent credit lines
 Age of oldest credit line in
months
 No. of credit enquiries in the
most recent 30 days
 No. of credit lines
 Debt-to-income ratio
Copyright © 2021 Dr. LAM Yat-fai 45
Label and all features, two class
 Label
 0: Survive
 1: Overdue or default
 Loan amount
 Loan purpose
 Debt consolidation
 Home improvement
 Job title
 No. of years at current job
 No. of major derogatory reports
 No. of delinquent credit lines
 Age of oldest credit line in months
 No. of credit enquiries
 Enquiries in the most recent 30 days
 No. of credit lines
 Debt-to-income ratio
Copyright © 2021 Dr. LAM Yat-fai 46
Chapter 5c2 – Sample data set (1)
 Datasets
 Chapter 5c1 – Full data set.csv
 Chapter 5c3 – Job title rank
 SMOTE
 Label column Default
 SMOTE percentage 124
 Edit Metadata
 Column Loan purpose, Job title
Copyright © 2021 Dr. LAM Yat-fai 47
Chapter 5c2 – Sample data set (2)
 Convert to Indicator Values
 Categorical columns Loan purpose
 Join Data
 Join key columns for Left Job title
 Join key columns for Right Job title
 Select Columns in Dataset
 All columns exclude Loan purpose, Loan purpose-
Loan Consolidation, Job title, Job title(2)
 Convert to CSV
Copyright © 2021 Dr. LAM Yat-fai 48
Feature selection
 Weak monotonicity
 Mortgage amount
 No. of credit lines
 Binary feature
 Loan purpose-Home improvement
 PCA cannot be applied
 No. of principal components
 9
Copyright © 2021 Dr. LAM Yat-fai 49
Chapter 5c4 – Prediction model (1)
 Datasets
 Chapter 5b2 – Sample data set
 Chapter 5b3 – Job title rank
 Edit Metadata
 Column Loan purpose, Job title
 Convert to Indicator Values
 Categorical columns Loan purpose
Copyright © 2021 Dr. LAM Yat-fai 50
Chapter 5c4 – Prediction model (2)
 Join Data
 Join key columns for Left Job title
 Join key columns for Right Job title
 Select Columns in Dataset
 All columns exclude Loan purpose, Loan purpose-
Loan Consolidation, Job title, Job title(2)
Copyright © 2021 Dr. LAM Yat-fai 51
Is overdue a weak form of default?
 Default
 Loan purpose
 No. of credit lines
 Overdue
 Loan amount
 No. of credit lines
Copyright © 2021 Dr. LAM Yat-fai 52
Creation of theory
 Hypothesis
 Overdue is a week form of default
 Testing
 H0: Overdue and default are caused by the same
set of features
 H0: Overdue and default are NOT caused by the
same set of features
 To be researched
Copyright © 2021 Dr. LAM Yat-fai 53

More Related Content

What's hot

Value-Based Payments and Managed Care Contracting - Crash Course Webinar Series
Value-Based Payments and Managed Care Contracting - Crash Course Webinar SeriesValue-Based Payments and Managed Care Contracting - Crash Course Webinar Series
Value-Based Payments and Managed Care Contracting - Crash Course Webinar SeriesEpstein Becker Green
 
Bragg Gaming Group Investor Deck November 2021
Bragg Gaming Group Investor Deck November 2021Bragg Gaming Group Investor Deck November 2021
Bragg Gaming Group Investor Deck November 2021RedChip Companies, Inc.
 
Outsourcing security survey0706 (1)
Outsourcing security survey0706 (1)Outsourcing security survey0706 (1)
Outsourcing security survey0706 (1)brijesh singh
 
Mountains of the Mind, Pension Funds greatest challenges in 2013 - Redington ...
Mountains of the Mind, Pension Funds greatest challenges in 2013 - Redington ...Mountains of the Mind, Pension Funds greatest challenges in 2013 - Redington ...
Mountains of the Mind, Pension Funds greatest challenges in 2013 - Redington ...Redington
 

What's hot (7)

1847 Holdings Investor Deck Dec. 2021
1847 Holdings Investor Deck Dec. 20211847 Holdings Investor Deck Dec. 2021
1847 Holdings Investor Deck Dec. 2021
 
Value-Based Payments and Managed Care Contracting - Crash Course Webinar Series
Value-Based Payments and Managed Care Contracting - Crash Course Webinar SeriesValue-Based Payments and Managed Care Contracting - Crash Course Webinar Series
Value-Based Payments and Managed Care Contracting - Crash Course Webinar Series
 
DeFi Technologies Deck - September 2021
DeFi Technologies Deck - September 2021DeFi Technologies Deck - September 2021
DeFi Technologies Deck - September 2021
 
Bragg Gaming Group Investor Deck November 2021
Bragg Gaming Group Investor Deck November 2021Bragg Gaming Group Investor Deck November 2021
Bragg Gaming Group Investor Deck November 2021
 
Outsourcing security survey0706 (1)
Outsourcing security survey0706 (1)Outsourcing security survey0706 (1)
Outsourcing security survey0706 (1)
 
Mountains of the Mind, Pension Funds greatest challenges in 2013 - Redington ...
Mountains of the Mind, Pension Funds greatest challenges in 2013 - Redington ...Mountains of the Mind, Pension Funds greatest challenges in 2013 - Redington ...
Mountains of the Mind, Pension Funds greatest challenges in 2013 - Redington ...
 
DeFi Technologies Deck
DeFi Technologies Deck DeFi Technologies Deck
DeFi Technologies Deck
 

Similar to Chapter 5 consumer lending

Chapter 6 corporate lending
Chapter 6   corporate lendingChapter 6   corporate lending
Chapter 6 corporate lendingQuan Risk
 
Chapter 4 microsoft azure machine learning studio
Chapter 4   microsoft azure machine learning studioChapter 4   microsoft azure machine learning studio
Chapter 4 microsoft azure machine learning studioQuan Risk
 
How To Biuld Internal Rating System For Basel Ii
How To Biuld Internal Rating System For Basel IiHow To Biuld Internal Rating System For Basel Ii
How To Biuld Internal Rating System For Basel IiFNian
 
Government and Education Webinar: Public Sector Cybersecurity Survey - What I...
Government and Education Webinar: Public Sector Cybersecurity Survey - What I...Government and Education Webinar: Public Sector Cybersecurity Survey - What I...
Government and Education Webinar: Public Sector Cybersecurity Survey - What I...SolarWinds
 
Implementing a Kenyan Credit Information Sharing System: Progress and Challe...
Implementing a Kenyan Credit Information Sharing System:  Progress and Challe...Implementing a Kenyan Credit Information Sharing System:  Progress and Challe...
Implementing a Kenyan Credit Information Sharing System: Progress and Challe...PERC
 
1 q13 small cap flipbook
1 q13 small cap flipbook1 q13 small cap flipbook
1 q13 small cap flipbookbennettlawrence
 
Financial Institutions PowerPoint Presentation Slides
Financial Institutions PowerPoint Presentation Slides Financial Institutions PowerPoint Presentation Slides
Financial Institutions PowerPoint Presentation Slides SlideTeam
 
Measuring Data Quality Return on Investment
Measuring Data Quality Return on InvestmentMeasuring Data Quality Return on Investment
Measuring Data Quality Return on InvestmentDATAVERSITY
 
CHAPTER 1Risk Management FundamentalsCopyright © 202
CHAPTER 1Risk Management FundamentalsCopyright © 202CHAPTER 1Risk Management FundamentalsCopyright © 202
CHAPTER 1Risk Management FundamentalsCopyright © 202EstelaJeffery653
 
MedTech Quality in the Age of Big Data - Are you ready?
MedTech Quality in the Age of Big Data - Are you ready?MedTech Quality in the Age of Big Data - Are you ready?
MedTech Quality in the Age of Big Data - Are you ready?Naveen Agarwal
 
Loan Analysis Predicting Defaulters
Loan Analysis Predicting DefaultersLoan Analysis Predicting Defaulters
Loan Analysis Predicting DefaultersIRJET Journal
 
Champion the Indian SaaS Story.pptx
Champion the Indian SaaS Story.pptxChampion the Indian SaaS Story.pptx
Champion the Indian SaaS Story.pptxSaaSBOOMi
 
Fight the good fight: Three lines of cyber defense working arm-in-arm
Fight the good fight: Three lines of cyber defense working arm-in-arm Fight the good fight: Three lines of cyber defense working arm-in-arm
Fight the good fight: Three lines of cyber defense working arm-in-arm Deloitte United States
 
BANK LOAN PREDICTION USING MACHINE LEARNING
BANK LOAN PREDICTION USING MACHINE LEARNINGBANK LOAN PREDICTION USING MACHINE LEARNING
BANK LOAN PREDICTION USING MACHINE LEARNINGIRJET Journal
 
apidays LIVE Hong Kong 2021 - Federated Learning for Banking by Isaac Wong, W...
apidays LIVE Hong Kong 2021 - Federated Learning for Banking by Isaac Wong, W...apidays LIVE Hong Kong 2021 - Federated Learning for Banking by Isaac Wong, W...
apidays LIVE Hong Kong 2021 - Federated Learning for Banking by Isaac Wong, W...apidays
 
cisco-privacy-benchmark-study-2023.pdf
cisco-privacy-benchmark-study-2023.pdfcisco-privacy-benchmark-study-2023.pdf
cisco-privacy-benchmark-study-2023.pdfAproximacionAlFuturo
 
Rules, institutions, or both? Explaining telecommunication investment in Lati...
Rules, institutions, or both? Explaining telecommunication investment in Lati...Rules, institutions, or both? Explaining telecommunication investment in Lati...
Rules, institutions, or both? Explaining telecommunication investment in Lati...AngelMelguizo
 

Similar to Chapter 5 consumer lending (20)

Chapter 6 corporate lending
Chapter 6   corporate lendingChapter 6   corporate lending
Chapter 6 corporate lending
 
Chapter 4 microsoft azure machine learning studio
Chapter 4   microsoft azure machine learning studioChapter 4   microsoft azure machine learning studio
Chapter 4 microsoft azure machine learning studio
 
How To Biuld Internal Rating System For Basel Ii
How To Biuld Internal Rating System For Basel IiHow To Biuld Internal Rating System For Basel Ii
How To Biuld Internal Rating System For Basel Ii
 
Government and Education Webinar: Public Sector Cybersecurity Survey - What I...
Government and Education Webinar: Public Sector Cybersecurity Survey - What I...Government and Education Webinar: Public Sector Cybersecurity Survey - What I...
Government and Education Webinar: Public Sector Cybersecurity Survey - What I...
 
Implementing a Kenyan Credit Information Sharing System: Progress and Challe...
Implementing a Kenyan Credit Information Sharing System:  Progress and Challe...Implementing a Kenyan Credit Information Sharing System:  Progress and Challe...
Implementing a Kenyan Credit Information Sharing System: Progress and Challe...
 
1 q13 small cap flipbook
1 q13 small cap flipbook1 q13 small cap flipbook
1 q13 small cap flipbook
 
Financial Institutions PowerPoint Presentation Slides
Financial Institutions PowerPoint Presentation Slides Financial Institutions PowerPoint Presentation Slides
Financial Institutions PowerPoint Presentation Slides
 
Measuring Data Quality Return on Investment
Measuring Data Quality Return on InvestmentMeasuring Data Quality Return on Investment
Measuring Data Quality Return on Investment
 
CHAPTER 1Risk Management FundamentalsCopyright © 202
CHAPTER 1Risk Management FundamentalsCopyright © 202CHAPTER 1Risk Management FundamentalsCopyright © 202
CHAPTER 1Risk Management FundamentalsCopyright © 202
 
MedTech Quality in the Age of Big Data - Are you ready?
MedTech Quality in the Age of Big Data - Are you ready?MedTech Quality in the Age of Big Data - Are you ready?
MedTech Quality in the Age of Big Data - Are you ready?
 
SP Five FF. ICBA handouts
SP Five FF. ICBA handoutsSP Five FF. ICBA handouts
SP Five FF. ICBA handouts
 
CECL is coming
CECL is comingCECL is coming
CECL is coming
 
Loan Analysis Predicting Defaulters
Loan Analysis Predicting DefaultersLoan Analysis Predicting Defaulters
Loan Analysis Predicting Defaulters
 
North delhi power limited
North delhi power limitedNorth delhi power limited
North delhi power limited
 
Champion the Indian SaaS Story.pptx
Champion the Indian SaaS Story.pptxChampion the Indian SaaS Story.pptx
Champion the Indian SaaS Story.pptx
 
Fight the good fight: Three lines of cyber defense working arm-in-arm
Fight the good fight: Three lines of cyber defense working arm-in-arm Fight the good fight: Three lines of cyber defense working arm-in-arm
Fight the good fight: Three lines of cyber defense working arm-in-arm
 
BANK LOAN PREDICTION USING MACHINE LEARNING
BANK LOAN PREDICTION USING MACHINE LEARNINGBANK LOAN PREDICTION USING MACHINE LEARNING
BANK LOAN PREDICTION USING MACHINE LEARNING
 
apidays LIVE Hong Kong 2021 - Federated Learning for Banking by Isaac Wong, W...
apidays LIVE Hong Kong 2021 - Federated Learning for Banking by Isaac Wong, W...apidays LIVE Hong Kong 2021 - Federated Learning for Banking by Isaac Wong, W...
apidays LIVE Hong Kong 2021 - Federated Learning for Banking by Isaac Wong, W...
 
cisco-privacy-benchmark-study-2023.pdf
cisco-privacy-benchmark-study-2023.pdfcisco-privacy-benchmark-study-2023.pdf
cisco-privacy-benchmark-study-2023.pdf
 
Rules, institutions, or both? Explaining telecommunication investment in Lati...
Rules, institutions, or both? Explaining telecommunication investment in Lati...Rules, institutions, or both? Explaining telecommunication investment in Lati...
Rules, institutions, or both? Explaining telecommunication investment in Lati...
 

More from Quan Risk

Chapter 1 the fatf's initiatives on aml
Chapter 1   the fatf's initiatives on amlChapter 1   the fatf's initiatives on aml
Chapter 1 the fatf's initiatives on amlQuan Risk
 
Chapter 10 control self-assessment
Chapter 10   control self-assessmentChapter 10   control self-assessment
Chapter 10 control self-assessmentQuan Risk
 
Chapter 9 private banking
Chapter 9   private bankingChapter 9   private banking
Chapter 9 private bankingQuan Risk
 
Chapter 8 career and professional development
Chapter 8   career and professional developmentChapter 8   career and professional development
Chapter 8 career and professional developmentQuan Risk
 
Chapter 7 regulatory technology
Chapter 7   regulatory technologyChapter 7   regulatory technology
Chapter 7 regulatory technologyQuan Risk
 
Chapter 6 aml compliance programme
Chapter 6   aml compliance programmeChapter 6   aml compliance programme
Chapter 6 aml compliance programmeQuan Risk
 
Chapter 5 internal investigation
Chapter 5   internal investigationChapter 5   internal investigation
Chapter 5 internal investigationQuan Risk
 
Chapter 4 supsicious transactions
Chapter 4   supsicious transactionsChapter 4   supsicious transactions
Chapter 4 supsicious transactionsQuan Risk
 
Chapter 3 know your customer
Chapter 3   know your customerChapter 3   know your customer
Chapter 3 know your customerQuan Risk
 
Chapter 2 the regulatory framework of aml
Chapter 2   the regulatory framework of amlChapter 2   the regulatory framework of aml
Chapter 2 the regulatory framework of amlQuan Risk
 
Chapter 6 career and professional development
Chapter 6   career and professional developmentChapter 6   career and professional development
Chapter 6 career and professional developmentQuan Risk
 
Chapter 5 financial compliance programme
Chapter 5   financial compliance programmeChapter 5   financial compliance programme
Chapter 5 financial compliance programmeQuan Risk
 
Chapter 4 securities and futures regulations
Chapter 4   securities and futures regulationsChapter 4   securities and futures regulations
Chapter 4 securities and futures regulationsQuan Risk
 
Chapter 3 insurance regulations
Chapter 3   insurance regulationsChapter 3   insurance regulations
Chapter 3 insurance regulationsQuan Risk
 
Chapter 2 banking regulations
Chapter 2   banking regulationsChapter 2   banking regulations
Chapter 2 banking regulationsQuan Risk
 
Chapter 1 financial regulations in hong kong
Chapter 1   financial regulations in hong kongChapter 1   financial regulations in hong kong
Chapter 1 financial regulations in hong kongQuan Risk
 
Chapter 10 aml technologies
Chapter 10   aml technologiesChapter 10   aml technologies
Chapter 10 aml technologiesQuan Risk
 
Chapter 9 anti-money laundering
Chapter 9   anti-money launderingChapter 9   anti-money laundering
Chapter 9 anti-money launderingQuan Risk
 
Chapter 7 algo trading and back testing
Chapter 7   algo trading and back testingChapter 7   algo trading and back testing
Chapter 7 algo trading and back testingQuan Risk
 
Chapter 6 machine learning regulatory technology
Chapter 6   machine learning regulatory technologyChapter 6   machine learning regulatory technology
Chapter 6 machine learning regulatory technologyQuan Risk
 

More from Quan Risk (20)

Chapter 1 the fatf's initiatives on aml
Chapter 1   the fatf's initiatives on amlChapter 1   the fatf's initiatives on aml
Chapter 1 the fatf's initiatives on aml
 
Chapter 10 control self-assessment
Chapter 10   control self-assessmentChapter 10   control self-assessment
Chapter 10 control self-assessment
 
Chapter 9 private banking
Chapter 9   private bankingChapter 9   private banking
Chapter 9 private banking
 
Chapter 8 career and professional development
Chapter 8   career and professional developmentChapter 8   career and professional development
Chapter 8 career and professional development
 
Chapter 7 regulatory technology
Chapter 7   regulatory technologyChapter 7   regulatory technology
Chapter 7 regulatory technology
 
Chapter 6 aml compliance programme
Chapter 6   aml compliance programmeChapter 6   aml compliance programme
Chapter 6 aml compliance programme
 
Chapter 5 internal investigation
Chapter 5   internal investigationChapter 5   internal investigation
Chapter 5 internal investigation
 
Chapter 4 supsicious transactions
Chapter 4   supsicious transactionsChapter 4   supsicious transactions
Chapter 4 supsicious transactions
 
Chapter 3 know your customer
Chapter 3   know your customerChapter 3   know your customer
Chapter 3 know your customer
 
Chapter 2 the regulatory framework of aml
Chapter 2   the regulatory framework of amlChapter 2   the regulatory framework of aml
Chapter 2 the regulatory framework of aml
 
Chapter 6 career and professional development
Chapter 6   career and professional developmentChapter 6   career and professional development
Chapter 6 career and professional development
 
Chapter 5 financial compliance programme
Chapter 5   financial compliance programmeChapter 5   financial compliance programme
Chapter 5 financial compliance programme
 
Chapter 4 securities and futures regulations
Chapter 4   securities and futures regulationsChapter 4   securities and futures regulations
Chapter 4 securities and futures regulations
 
Chapter 3 insurance regulations
Chapter 3   insurance regulationsChapter 3   insurance regulations
Chapter 3 insurance regulations
 
Chapter 2 banking regulations
Chapter 2   banking regulationsChapter 2   banking regulations
Chapter 2 banking regulations
 
Chapter 1 financial regulations in hong kong
Chapter 1   financial regulations in hong kongChapter 1   financial regulations in hong kong
Chapter 1 financial regulations in hong kong
 
Chapter 10 aml technologies
Chapter 10   aml technologiesChapter 10   aml technologies
Chapter 10 aml technologies
 
Chapter 9 anti-money laundering
Chapter 9   anti-money launderingChapter 9   anti-money laundering
Chapter 9 anti-money laundering
 
Chapter 7 algo trading and back testing
Chapter 7   algo trading and back testingChapter 7   algo trading and back testing
Chapter 7 algo trading and back testing
 
Chapter 6 machine learning regulatory technology
Chapter 6   machine learning regulatory technologyChapter 6   machine learning regulatory technology
Chapter 6 machine learning regulatory technology
 

Recently uploaded

High Class Call Girls Nagpur Grishma Call 7001035870 Meet With Nagpur Escorts
High Class Call Girls Nagpur Grishma Call 7001035870 Meet With Nagpur EscortsHigh Class Call Girls Nagpur Grishma Call 7001035870 Meet With Nagpur Escorts
High Class Call Girls Nagpur Grishma Call 7001035870 Meet With Nagpur Escortsranjana rawat
 
Financial institutions facilitate financing, economic transactions, issue fun...
Financial institutions facilitate financing, economic transactions, issue fun...Financial institutions facilitate financing, economic transactions, issue fun...
Financial institutions facilitate financing, economic transactions, issue fun...Avanish Goel
 
The Triple Threat | Article on Global Resession | Harsh Kumar
The Triple Threat | Article on Global Resession | Harsh KumarThe Triple Threat | Article on Global Resession | Harsh Kumar
The Triple Threat | Article on Global Resession | Harsh KumarHarsh Kumar
 
Chapter 2.ppt of macroeconomics by mankiw 9th edition
Chapter 2.ppt of macroeconomics by mankiw 9th editionChapter 2.ppt of macroeconomics by mankiw 9th edition
Chapter 2.ppt of macroeconomics by mankiw 9th editionMuhammadHusnain82237
 
VIP Call Girls Service Dilsukhnagar Hyderabad Call +91-8250192130
VIP Call Girls Service Dilsukhnagar Hyderabad Call +91-8250192130VIP Call Girls Service Dilsukhnagar Hyderabad Call +91-8250192130
VIP Call Girls Service Dilsukhnagar Hyderabad Call +91-8250192130Suhani Kapoor
 
Andheri Call Girls In 9825968104 Mumbai Hot Models
Andheri Call Girls In 9825968104 Mumbai Hot ModelsAndheri Call Girls In 9825968104 Mumbai Hot Models
Andheri Call Girls In 9825968104 Mumbai Hot Modelshematsharma006
 
BPPG response - Options for Defined Benefit schemes - 19Apr24.pdf
BPPG response - Options for Defined Benefit schemes - 19Apr24.pdfBPPG response - Options for Defined Benefit schemes - 19Apr24.pdf
BPPG response - Options for Defined Benefit schemes - 19Apr24.pdfHenry Tapper
 
Lundin Gold April 2024 Corporate Presentation v4.pdf
Lundin Gold April 2024 Corporate Presentation v4.pdfLundin Gold April 2024 Corporate Presentation v4.pdf
Lundin Gold April 2024 Corporate Presentation v4.pdfAdnet Communications
 
House of Commons ; CDC schemes overview document
House of Commons ; CDC schemes overview documentHouse of Commons ; CDC schemes overview document
House of Commons ; CDC schemes overview documentHenry Tapper
 
Monthly Market Risk Update: April 2024 [SlideShare]
Monthly Market Risk Update: April 2024 [SlideShare]Monthly Market Risk Update: April 2024 [SlideShare]
Monthly Market Risk Update: April 2024 [SlideShare]Commonwealth
 
VIP Kolkata Call Girl Jodhpur Park 👉 8250192130 Available With Room
VIP Kolkata Call Girl Jodhpur Park 👉 8250192130  Available With RoomVIP Kolkata Call Girl Jodhpur Park 👉 8250192130  Available With Room
VIP Kolkata Call Girl Jodhpur Park 👉 8250192130 Available With Roomdivyansh0kumar0
 
call girls in Nand Nagri (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in  Nand Nagri (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in  Nand Nagri (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Nand Nagri (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Call Girls In Yusuf Sarai Women Seeking Men 9654467111
Call Girls In Yusuf Sarai Women Seeking Men 9654467111Call Girls In Yusuf Sarai Women Seeking Men 9654467111
Call Girls In Yusuf Sarai Women Seeking Men 9654467111Sapana Sha
 
government_intervention_in_business_ownership[1].pdf
government_intervention_in_business_ownership[1].pdfgovernment_intervention_in_business_ownership[1].pdf
government_intervention_in_business_ownership[1].pdfshaunmashale756
 
Instant Issue Debit Cards - School Designs
Instant Issue Debit Cards - School DesignsInstant Issue Debit Cards - School Designs
Instant Issue Debit Cards - School Designsegoetzinger
 
OAT_RI_Ep19 WeighingTheRisks_Apr24_TheYellowMetal.pptx
OAT_RI_Ep19 WeighingTheRisks_Apr24_TheYellowMetal.pptxOAT_RI_Ep19 WeighingTheRisks_Apr24_TheYellowMetal.pptx
OAT_RI_Ep19 WeighingTheRisks_Apr24_TheYellowMetal.pptxhiddenlevers
 
Vip B Aizawl Call Girls #9907093804 Contact Number Escorts Service Aizawl
Vip B Aizawl Call Girls #9907093804 Contact Number Escorts Service AizawlVip B Aizawl Call Girls #9907093804 Contact Number Escorts Service Aizawl
Vip B Aizawl Call Girls #9907093804 Contact Number Escorts Service Aizawlmakika9823
 
VIP Call Girls LB Nagar ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With Room...
VIP Call Girls LB Nagar ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With Room...VIP Call Girls LB Nagar ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With Room...
VIP Call Girls LB Nagar ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With Room...Suhani Kapoor
 
Malad Call Girl in Services 9892124323 | ₹,4500 With Room Free Delivery
Malad Call Girl in Services  9892124323 | ₹,4500 With Room Free DeliveryMalad Call Girl in Services  9892124323 | ₹,4500 With Room Free Delivery
Malad Call Girl in Services 9892124323 | ₹,4500 With Room Free DeliveryPooja Nehwal
 

Recently uploaded (20)

High Class Call Girls Nagpur Grishma Call 7001035870 Meet With Nagpur Escorts
High Class Call Girls Nagpur Grishma Call 7001035870 Meet With Nagpur EscortsHigh Class Call Girls Nagpur Grishma Call 7001035870 Meet With Nagpur Escorts
High Class Call Girls Nagpur Grishma Call 7001035870 Meet With Nagpur Escorts
 
🔝9953056974 🔝Call Girls In Dwarka Escort Service Delhi NCR
🔝9953056974 🔝Call Girls In Dwarka Escort Service Delhi NCR🔝9953056974 🔝Call Girls In Dwarka Escort Service Delhi NCR
🔝9953056974 🔝Call Girls In Dwarka Escort Service Delhi NCR
 
Financial institutions facilitate financing, economic transactions, issue fun...
Financial institutions facilitate financing, economic transactions, issue fun...Financial institutions facilitate financing, economic transactions, issue fun...
Financial institutions facilitate financing, economic transactions, issue fun...
 
The Triple Threat | Article on Global Resession | Harsh Kumar
The Triple Threat | Article on Global Resession | Harsh KumarThe Triple Threat | Article on Global Resession | Harsh Kumar
The Triple Threat | Article on Global Resession | Harsh Kumar
 
Chapter 2.ppt of macroeconomics by mankiw 9th edition
Chapter 2.ppt of macroeconomics by mankiw 9th editionChapter 2.ppt of macroeconomics by mankiw 9th edition
Chapter 2.ppt of macroeconomics by mankiw 9th edition
 
VIP Call Girls Service Dilsukhnagar Hyderabad Call +91-8250192130
VIP Call Girls Service Dilsukhnagar Hyderabad Call +91-8250192130VIP Call Girls Service Dilsukhnagar Hyderabad Call +91-8250192130
VIP Call Girls Service Dilsukhnagar Hyderabad Call +91-8250192130
 
Andheri Call Girls In 9825968104 Mumbai Hot Models
Andheri Call Girls In 9825968104 Mumbai Hot ModelsAndheri Call Girls In 9825968104 Mumbai Hot Models
Andheri Call Girls In 9825968104 Mumbai Hot Models
 
BPPG response - Options for Defined Benefit schemes - 19Apr24.pdf
BPPG response - Options for Defined Benefit schemes - 19Apr24.pdfBPPG response - Options for Defined Benefit schemes - 19Apr24.pdf
BPPG response - Options for Defined Benefit schemes - 19Apr24.pdf
 
Lundin Gold April 2024 Corporate Presentation v4.pdf
Lundin Gold April 2024 Corporate Presentation v4.pdfLundin Gold April 2024 Corporate Presentation v4.pdf
Lundin Gold April 2024 Corporate Presentation v4.pdf
 
House of Commons ; CDC schemes overview document
House of Commons ; CDC schemes overview documentHouse of Commons ; CDC schemes overview document
House of Commons ; CDC schemes overview document
 
Monthly Market Risk Update: April 2024 [SlideShare]
Monthly Market Risk Update: April 2024 [SlideShare]Monthly Market Risk Update: April 2024 [SlideShare]
Monthly Market Risk Update: April 2024 [SlideShare]
 
VIP Kolkata Call Girl Jodhpur Park 👉 8250192130 Available With Room
VIP Kolkata Call Girl Jodhpur Park 👉 8250192130  Available With RoomVIP Kolkata Call Girl Jodhpur Park 👉 8250192130  Available With Room
VIP Kolkata Call Girl Jodhpur Park 👉 8250192130 Available With Room
 
call girls in Nand Nagri (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in  Nand Nagri (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in  Nand Nagri (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Nand Nagri (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
 
Call Girls In Yusuf Sarai Women Seeking Men 9654467111
Call Girls In Yusuf Sarai Women Seeking Men 9654467111Call Girls In Yusuf Sarai Women Seeking Men 9654467111
Call Girls In Yusuf Sarai Women Seeking Men 9654467111
 
government_intervention_in_business_ownership[1].pdf
government_intervention_in_business_ownership[1].pdfgovernment_intervention_in_business_ownership[1].pdf
government_intervention_in_business_ownership[1].pdf
 
Instant Issue Debit Cards - School Designs
Instant Issue Debit Cards - School DesignsInstant Issue Debit Cards - School Designs
Instant Issue Debit Cards - School Designs
 
OAT_RI_Ep19 WeighingTheRisks_Apr24_TheYellowMetal.pptx
OAT_RI_Ep19 WeighingTheRisks_Apr24_TheYellowMetal.pptxOAT_RI_Ep19 WeighingTheRisks_Apr24_TheYellowMetal.pptx
OAT_RI_Ep19 WeighingTheRisks_Apr24_TheYellowMetal.pptx
 
Vip B Aizawl Call Girls #9907093804 Contact Number Escorts Service Aizawl
Vip B Aizawl Call Girls #9907093804 Contact Number Escorts Service AizawlVip B Aizawl Call Girls #9907093804 Contact Number Escorts Service Aizawl
Vip B Aizawl Call Girls #9907093804 Contact Number Escorts Service Aizawl
 
VIP Call Girls LB Nagar ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With Room...
VIP Call Girls LB Nagar ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With Room...VIP Call Girls LB Nagar ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With Room...
VIP Call Girls LB Nagar ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With Room...
 
Malad Call Girl in Services 9892124323 | ₹,4500 With Room Free Delivery
Malad Call Girl in Services  9892124323 | ₹,4500 With Room Free DeliveryMalad Call Girl in Services  9892124323 | ₹,4500 With Room Free Delivery
Malad Call Girl in Services 9892124323 | ₹,4500 With Room Free Delivery
 

Chapter 5 consumer lending

  • 1. Chapter 5 Consumer Lending The Presentation Slides for Teaching Regulatory Technology Website : https://sites.google.com/site/quanrisk E-mail : quanrisk@gmail.com Copyright © 2021 Dr. LAM Yat-fai
  • 2. Declaration  Copyright © 2021 Dr. LAM Yat-fai  All rights reserved. No part of this presentation file may be reproduced, in any form or by any means, without written permission from Dr. LAM Yat-fai.  Authored by Dr. LAM Yat-fai (林日辉), Chief Data Scientist, CapitaLogic Limited, Adjunct Professor of Finance, City University of Hong Kong, Doctor of Business Administration, CFA, CAIA, CAMS, CFE, FRM, PRM, MCSE, MCNE. Copyright © 2021 Dr. LAM Yat-fai 2
  • 3. Outline  Sample data set  Regulatory requirements  Model development  Default prediction model  Overdue prediction model Copyright © 2021 Dr. LAM Yat-fai 3
  • 4. Two class sampling techniques  For machine learning theories  50% to 50%  Real full data set  30% to 70%  20% to 80%  Under sampling  Reduce the majority class to match the minority class  Over sampling  Increase the minority class to match the majority class Copyright © 2021 Dr. LAM Yat-fai 4
  • 5. Full data set Copyright © 2021 Dr. LAM Yat-fai 5
  • 6. Under sampling Copyright © 2021 Dr. LAM Yat-fai 6
  • 7. Over sampling Copyright © 2021 Dr. LAM Yat-fai 7
  • 8. SMOTE  Synthetic Minority Oversampling Technique  Create new records from existing minority class  For each record of minority class  Substitute the value of a feature with the value of a record nearby Copyright © 2021 Dr. LAM Yat-fai 8
  • 9. Feature type  Numeric  Continuous feature Annual income  Discrete feature No. of children  Non-numeric  Binary feature Gender  Categorical feature Education Copyright © 2021 Dr. LAM Yat-fai 9
  • 10. Binary feature  Gender  Male 0  Female 1  Martial status  Single 0  Married 1 Copyright © 2021 Dr. LAM Yat-fai 10
  • 11. Categorical feature  Education  Postgraduate  Undergraduate  Secondary school  Primary school  No education  Country  United States  United Kingdom  Canada  Australia  China Copyright © 2021 Dr. LAM Yat-fai 11
  • 12. Assign ranks to categorical variable Country Label average Rank Australia 0.21 5 Canada 0.63 1 China 0.49 3 United Kingdom 0.38 4 United States 0.52 2 Copyright © 2021 Dr. LAM Yat-fai 12
  • 13. Chapter 5a2 – Sample data set (1)  Datasets  Chapter 5a1 – Full data set.csv  Chapter 5a3 – Country rank  SMOTE  Label column y  SMOTE percentage 58  Edit Metadata  Column Gender, Country Copyright © 2021 Dr. LAM Yat-fai 13
  • 14. Chapter 5a2 – Sample data set (2)  Convert to Indicator Values  Categorical columns Gender  Join Data  Join key columns for Left Country  Join key columns for Right Country  Select Columns in Dataset  All columns exclude Gender, Gender-Male, Country, Country(2)  Convert to CSV Copyright © 2021 Dr. LAM Yat-fai 14
  • 15. Outline  Sample data set  Regulatory requirements  Model development  Default prediction model  Overdue prediction model Copyright © 2021 Dr. LAM Yat-fai 15
  • 16. Banking activities Deposits < 1% Shareholders’ equity Dividend + equity price appreciation 3% - 20% Term loans, credit cards, mortgages Bank Copyright © 2021 Dr. LAM Yat-fai 16
  • 17. Major retail lending products  Term loan  Fixed loan principal  No collateral  Credit card  Subject to a credit limit  No collateral  Residential mortgage  Principal amortization  Property as collateral Copyright © 2021 Dr. LAM Yat-fai 17
  • 18. HKMA SPM CR-G-1 General Principles of Credit Risk Management  4.1.4 Credit decisions should be supported by adequate evaluation of the borrower's repayment ability based on reliable information. Sufficient and up-to-date information should continue to be available to enable effective monitoring of the account. Copyright © 2021 Dr. LAM Yat-fai 18
  • 19. Commercial Banks Law, PRC  Article 35. Before granting a loan, commercial banks shall strictly examine the borrower's purpose for the loan, ability to repay the loan, method of repayment, etc. . Copyright © 2021 Dr. LAM Yat-fai 19
  • 20. 20 Default  Generic definition  A borrower fails to pay to the lender the interest and/or principal in full on schedule  Regulatory definition  A borrower fails to pay to the lender the interest and/or principal within 90 days of the due date
  • 21. 21 Survival → overdue → default Survival Overdue Default Payment Payment Yes Yes No No 90 days
  • 22. Risk management objectives  To predict whether a borrower will default in the following one year  Good, bad  Good, moderate, bad  Good, good to moderate, moderate to bad, bad  Probability of default Copyright © 2021 Dr. LAM Yat-fai 22
  • 23. Regulatory and legal constraints  Interpretability  The relationship between the label and features can be well established by experience and theory  No violation with common sense unless the common sense is inapplicable  Equal opportunity  Religion, race, disability … cannot be used directly as a feature, as mandated by anti- discrimination law Copyright © 2021 Dr. LAM Yat-fai 23
  • 24. Outline  Sample data set  Regulatory requirements  Model development  Default prediction model  Overdue prediction model Copyright © 2021 Dr. LAM Yat-fai 24
  • 25. Standard procedure (1)  Analyze regulatory requirements  Collect historical records  Prepare sample data set  Over sampling  Convert binary features into [0,1]  Convert categorical features into ranks Copyright © 2021 Dr. LAM Yat-fai 25
  • 26. Standard procedure (2)  Assess monotonicity and principal components  Develop machine learning model  Evaluate model performance  Create prediction model  Assess sample, positive class and negative class accuracies  Conduct prediction Copyright © 2021 Dr. LAM Yat-fai 26
  • 27. Modelling assumptions  Many historical borrower records  Many borrowers survive in one year  Some borrowers default in one year  There is a monotonic relationship between  Label: whether a borrower defaults in one year  Features: borrower information collected one year ago Copyright © 2021 Dr. LAM Yat-fai 27
  • 28. Label  0  The borrower survives in one year  1  The borrower defaults in one year Copyright © 2021 Dr. LAM Yat-fai 28
  • 29. Features  From application form  Personal data  Employment data  Income data  Asset data  Liability data Copyright © 2021 Dr. LAM Yat-fai 29
  • 30. Expected monotonicity  Strong  Annual income, outstanding loan, equity investments  To be verified by data  Weak or unknown  Education, gender, martial status  To be determined by data  No  ID card no., telephone no., application date  To be ignored Copyright © 2021 Dr. LAM Yat-fai 30
  • 31. Data dictionary  Label  Survive (0) or Default (1)  Description  The default status of a borrower in one year after his features were collected  Label type  Binary Copyright © 2021 Dr. LAM Yat-fai 31
  • 32. Data dictionary  Feature  Income  Description  The total income during the last 12 month, including fixed salary, commission and bonus, after income tax and pension contribution have been deducted  Feature type  Continuous value  Expected impact to default  Strong  Negative Copyright © 2021 Dr. LAM Yat-fai 32
  • 33. Data dictionary  Feature  Loan amount  Description  The outstanding loan amount  Feature type  Continuous value  Expected impact to default  Strong  Positive Copyright © 2021 Dr. LAM Yat-fai 33
  • 34. Outline  Sample data set  Regulatory requirements  Model development  Default prediction model  Overdue prediction model Copyright © 2021 Dr. LAM Yat-fai 34
  • 35. Two class PD model           1 2 3 N Default Default Default Default 1 2 3 U Survive Survive Survive Survive 1 2 3 V PD = F x , x ,x , , x Maximize L = PD × PD × PD × × PD × 1 - PD × 1 - PD × 1 - PD × × 1 - PD 35 Copyright © 2020 CapitaLogic Limited
  • 36. Full data set  Feature  Data on existing mortgage borrowers one year ago  Label  Either survives or defaults in one year  Several thousand records  Imbalanced  Some features missed  Some records duplicated Copyright © 2021 Dr. LAM Yat-fai 36
  • 37. Label and all features  Label  0: Survives in the last year  1: Defaults in the last year  Loan amount  Loan purpose  Debt consolidation  Home improvement  Job title  No. of years at current job  No. of major derogatory reports  No. of delinquent credit lines  Age of oldest credit line in months  No. of credit enquiries in the most recent 30 days  No. of credit lines  Debt-to-income ratio Copyright © 2021 Dr. LAM Yat-fai 37
  • 38. Chapter 5b2 – Sample data set (1)  Datasets  Chapter 5b1 – Full data set.csv  Chapter 5b3 – Job title rank  SMOTE  Label column Default  SMOTE percentage 57  Edit Metadata  Column Loan purpose, Job title Copyright © 2021 Dr. LAM Yat-fai 38
  • 39. Chapter 5B2 – Sample data set (2)  Convert to Indicator Values  Categorical columns Loan purpose  Join Data  Join key columns for Left Job title  Join key columns for Right Job title  Save as Dataset  Select Columns in Dataset  All columns exclude Loan purpose, Loan purpose- Loan Consolidation, Job title, Job title(2)  Convert to CSV Copyright © 2021 Dr. LAM Yat-fai 39
  • 40. Feature selection  Weak monotonicity  Mortgage amount  No. of credit lines  Loan purpose-Home  No. of principal components  8 Copyright © 2021 Dr. LAM Yat-fai 40
  • 41. Chapter 5b4 – Prediction model  Datasets  Chapter 5b2 – Sample data set  Chapter 5b3 – Job title rank  Edit Metadata  Column Job title  Join Data  Join key columns for Left Job title  Join key columns for Right Job title  Select Columns in Dataset  All columns exclude Loan purpose, Job title, Job title(2) Copyright © 2021 Dr. LAM Yat-fai 41
  • 42. Other standard procedures  Run training experiment  Create predictive experiment  Modify Web service input and Web service output  Run predictive experiment  Deploy web service  Download Excel prediction model  Upload Excel prediction model to OneDrive  Conduct assessment and prediction Copyright © 2021 Dr. LAM Yat-fai 42
  • 43. Excel prediction model  5 samples test  All samples accuracy  Overall accuracy  Survive class accuracy, full data set  Upper cutoff score  Defaulted class accuracy, full data set  Lower cutoff score  Prediction Copyright © 2021 Dr. LAM Yat-fai 43
  • 44. Outline  Sample data set  Regulatory requirements  Model development  Default prediction model  Overdue prediction model Copyright © 2021 Dr. LAM Yat-fai 44
  • 45. Label and all features, three class  Label  Survive  Overdue  Default  Loan amount  Loan purpose  Debt consolidation  Home improvement  Job title  No. of years at current job  No. of major derogatory reports  No. of delinquent credit lines  Age of oldest credit line in months  No. of credit enquiries in the most recent 30 days  No. of credit lines  Debt-to-income ratio Copyright © 2021 Dr. LAM Yat-fai 45
  • 46. Label and all features, two class  Label  0: Survive  1: Overdue or default  Loan amount  Loan purpose  Debt consolidation  Home improvement  Job title  No. of years at current job  No. of major derogatory reports  No. of delinquent credit lines  Age of oldest credit line in months  No. of credit enquiries  Enquiries in the most recent 30 days  No. of credit lines  Debt-to-income ratio Copyright © 2021 Dr. LAM Yat-fai 46
  • 47. Chapter 5c2 – Sample data set (1)  Datasets  Chapter 5c1 – Full data set.csv  Chapter 5c3 – Job title rank  SMOTE  Label column Default  SMOTE percentage 124  Edit Metadata  Column Loan purpose, Job title Copyright © 2021 Dr. LAM Yat-fai 47
  • 48. Chapter 5c2 – Sample data set (2)  Convert to Indicator Values  Categorical columns Loan purpose  Join Data  Join key columns for Left Job title  Join key columns for Right Job title  Select Columns in Dataset  All columns exclude Loan purpose, Loan purpose- Loan Consolidation, Job title, Job title(2)  Convert to CSV Copyright © 2021 Dr. LAM Yat-fai 48
  • 49. Feature selection  Weak monotonicity  Mortgage amount  No. of credit lines  Binary feature  Loan purpose-Home improvement  PCA cannot be applied  No. of principal components  9 Copyright © 2021 Dr. LAM Yat-fai 49
  • 50. Chapter 5c4 – Prediction model (1)  Datasets  Chapter 5b2 – Sample data set  Chapter 5b3 – Job title rank  Edit Metadata  Column Loan purpose, Job title  Convert to Indicator Values  Categorical columns Loan purpose Copyright © 2021 Dr. LAM Yat-fai 50
  • 51. Chapter 5c4 – Prediction model (2)  Join Data  Join key columns for Left Job title  Join key columns for Right Job title  Select Columns in Dataset  All columns exclude Loan purpose, Loan purpose- Loan Consolidation, Job title, Job title(2) Copyright © 2021 Dr. LAM Yat-fai 51
  • 52. Is overdue a weak form of default?  Default  Loan purpose  No. of credit lines  Overdue  Loan amount  No. of credit lines Copyright © 2021 Dr. LAM Yat-fai 52
  • 53. Creation of theory  Hypothesis  Overdue is a week form of default  Testing  H0: Overdue and default are caused by the same set of features  H0: Overdue and default are NOT caused by the same set of features  To be researched Copyright © 2021 Dr. LAM Yat-fai 53