hdfc bank ppt
TRANSCRIPT
© Experian Limited 2007. All rights reserved. Experian and the marks used herein are service marks or registered trademarks of Experian Limited. Other product and company names mentioned herein may be the trademarks of their respective owners. No part of this copyrighted work may be reproduced, modified, or distributed in any form or manner without the prior written permission of Experian Limited.Confidential and proprietary.
Best practice in data & scoring
Dr Paul RussellDirector Analytical Solutions
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 2
Agenda
Some themes
Analytics and the customer life cycle
The role of scoring
Building a scorecard
Using scoring systems
Risk management infrastructure
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 3
Best practice is often discussed but almost never seen
Do the simple things well
Risk management is more than just a scorecard
The same principles apply across the credit lifecycle
Themes
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 4
New customers
1. Identifying potential customers;
2. Selling credit products to new customers;
3. Identifying the credit risk of the customer and the proposed transaction;
4. Identifying the risk of fraudulent application
5. Deciding whether to accept or decline the transaction;
6. Deciding, for accepted transactions, on the terms, e.g., credit amount, pricing.
Existing, non-delinquent customers
7. Reviewing the customers facilities (e.g., credit limits, price, etc.);
8. Cross-selling new products to the customers;
9. Ensuring good customers are retained;
10. Identify fraudulent transactions.
Existing, delinquent customers
11. Identifying self-cure customers;
12. Rehabilitation of potentially good customers;
13. Work-out customers where relationship is broken.
Target population Description
Credit process step
Customer acquisitionCustomer acquisition
Customer managementCustomer management
CollectionsCollections
13 ways to grow bad debt
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 5
Why is credit risk management important?
Get it right and it can support phenomenal value creation
European consumer finance business, Profit Before Tax and Impairment Charges ($m)
Source: Annual Reports
Impairment charges
Profits
676802 836
1,094
1,230
1,382
764
2,196
2,986
1,374
1,520
1,522
924804
740
478340288
1998 1999 2000 2001 2002 2003 2004 2005 2006
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 6
Data
Statistical Models
Credit strategies
Implementation tools
Evaluation tools
Component Description
Application data (for new customers)Account behaviour data (for existing customers)External data (e.g., credit bureaux)
Risk models (PD, LGD), fraud models (application and transaction fraud) and revenue models
Business rules that translate the outcome of statistical models in credit decisions (accept/decline, price, credit limits, etc.) that maximise profit
Software tools to automate the calculation of the above scores and credit strategies on-line on high volumes, with a high degree of flexibility to change credit strategies “on the fly”
Software tools to evaluate the performance of statistical models and credit strategies, and accuracy of implementation
5 core components
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 7
Agenda
Some basic themes
Analytics and the customer life cycle
The role of scoring
Building a scorecard
Using scoring systems
Risk management infrastructure
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 8
Analytics and the customer life cycle
Solicitation Debtrecovery
Application Customermanagement
Collections
Population
Information
Analytics touches every part of the customer lifecycle
Analytics touches every part of the customer life cycle
Amount of information about the customer grows as the relationship advances through the customer life cycle
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 9
Analytics and the customer life cycle
• Channel preference
• Contact history
• Demographics
• Location
• Bureau data
• Action outcomes
• Costs
• Channel
• Product holdings
• Demographics
• Bureau data
• Previous relationships
• Account performance
• Costs
• Product holdings
• Usage
• Delinquency
• Customer contacts
• Preferences
• Bureau data
• Actions taken
• Action outcomes
• Costs
• Action history
• Promises to pay
• Promises fulfilled
• Action outcomes
• Bureau data
• Costs
• Action history
• Promises to pay
• Bureau data
• Agents used
• Promises fulfilled
• Litigation outcomes
• Costs
Solicitation Debtrecovery
Application Customermanagement
Collections
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 10
Analytics and the customer life cycle
Strategy Review
Plan
Define GoalsAgree objectives
Review
Assess current challenger
Design
Build new strategy
Implement
Ensure operational deployment
Monitor
Track progress against expectations
Assess
Understand results
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 11
Agenda
Some basic themes
Analytics and the customer life cycle
The role of scoring
Building a scorecard
Using scoring systems
Risk management infrastructure
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 12
The role of scoring
Credit scoring is a technique for predicting the future
This prediction can be anything of importance to the business Arrears Fraud Profit Response Account closure Company failure Etc.
All scoring is based on one key assumption: The past predicts the future
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 13
The role of scoring
How does scoring work?
• Scorecards add and subtract points to a baseline constant according to individual’s or account’s data
• Scorecards are easy to apply and simple to understand
• The resulting score gives a prediction of future behaviour
• Scores are used to rank individuals to assign the best actions
Baseline Constant 800
Applicant Age in Years
< 22 -50
22 - 25 -20
26 – 40 0
41 – 55 +30
> 55 0
Worst Status L6M (on all Accounts)
0 0
1 - 2 -45
3+ -100
Joint Applicant Present
Y +20
N 0
Etc. Etc.
… …
Example Scorecard
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 14
The role of scoring – application scorecard
• Consider a scorecard built to predict whether a new applicant for a credit product will default in the next 12 months
• This scorecard is used when a new customer applies…
Application Form Data
External Data(Bureau etc.)
Score-card Score
Take most appropriate action for each individual
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 15
The role of scoring - scores can drive actions
Application Score
Pro
po
rtio
n o
f A
pp
lican
ts
Low Score / High Risk
High Score / Low Risk
Extremely High Risk
Reject
High Risk
Reject or price to cover the high expected loss
Standard Risk
Accept on standard terms
Extremely Low Risk
Consider for cross-sell of other
products
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 16
The role of scoring - benefits
Best use of data
Objective
Consistent
Automation
Control
Reduced losses
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 17
Agenda
Some basic themes
Analytics and the customer life cycle
The role of scoring
Building a scorecard
Using scoring systems
Risk management infrastructure
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 18
Building a scorecard – 3 requirements
Development sample – the historical data on which the scorecard will be built
Outcome – what we are trying to predict
Modelling methodology – the statistical tool that will help us form our scoring model
Some time laterThe recent past
TH
EN
NO
W
Development Sample
Outcome
Score-cardStatistical Model
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 19
Is my sample any good?
Representative Products Business cycle The future
Robust Volumes
Mature
Is the outcome reliable?
The recent past
TH
EN
Development Sample
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 20
Building a scorecard – the development sample
The recent past
TH
EN
Development Sample
• This data can come from a number of sources• All relevant data should go into the development sample
ApplicationForm
Information collected from the applicant at the application
point
CreditBureau
Data
Information on the individual’s
other credit commitments
HistoricalAccount
Behaviour
Information on the historical behaviour on the account
OtherAccount
Information
Information on the historical behaviour on
other accounts with the same
lender
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 21
Building a scorecard – the outcome
This is the behaviour that we are trying to predict
NO
W
Outcome
• Can be a continuous variable (profit, revenue, loss given default, etc.)
• More commonly it is dichotomous - yes/no Will this applicant default? Is this transaction fraudulent? Will this company fail? Etc.
THE FUTURE
Observation - Now
Good
Outcome - Prediction
Bad
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 22
What are we trying to predict?
Bad Good
Consumer 3 payments in arrears
Not 3 payments in arrears
Limited business Failed Still going
Non-limited business Bankruptcy, court judgements or
defaults
No bankruptcy, court judgements
or defaults
NO
W
Outcome
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 23
Building a scorecard – the statistical model
Many statistical tools available
Data is the most important factorStatistical Model
Observation Data Outcome Statistical ModelScore-card
Statistical tool needs to be:
Powerful – to get the best prediction from the data
Flexible – can handle varying data types and outcomes
Interpretable – easy to understand and to overlay business intelligence
Transparent – should be non-’black box’ for regulatory reasons and to ensure understanding
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 24
Building a scorecard - the statistical model
Linear regression
Logistic regression
Artificial neural networks
Etc
Other things being equal the choice of algorithm has relatively little impact on the ultimate power of the model
Statistical Model
xx
xx
xx
x
x
xxx
xx
x
x
x x
xx
x
x
Prediction
Rea
lity
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 25
Building a scorecard – assessing the model
Does the model solve the business problem?
Discrimination – the power to polarise individuals between good and bad - Gini statistic & Kolmogorov-Smirnov statistic
Accuracy – how much of the variability of the outcome is explained by the model
Validation – ensures that over-modelling has not occurred or that an anomalous sample has not been used
Improvement – the new model should outperforms the existing model
Statistical Model
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 26
Agenda
Some basic themes
Analytics and the customer life cycle
The role of scoring
Building a scorecard
Using scoring systems
Risk management infrastructure
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 27
Using scoring systems
The data feeds the scoring system, which is used to aid the decisioning
The decisions a company makes determine its strategy
It is the aims and strategy of the business that must be considered when deciding how to use a scoring system, e.g.
Growing the market share Reducing bad debt Increasing automation Maximising response for given marketing cost Combating fraud
DATASCORECARD
STRATEGYDECISIONS
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 28
The role of scoring - scores can drive actions
Application Score
Pro
po
rtio
n o
f A
pp
lican
ts
Low Score / High Risk
High Score / Low Risk
Extremely High Risk
Reject
High Risk
Reject or price to cover the high expected loss
Standard Risk
Accept on standard terms
Extremely Low Risk
Consider for cross-sell of other
products
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 29
Using scoring systems - the score distribution
Score Band # Goods # Bads GB Odds % Applicants
≤ 400 500 500 1 9.8
401 – 550 700 350 2 10.3
551 – 650 815 163 5 9.6
651 – 700 1008 84 12 10.7
701 – 750 976 61 16 10.1
751 - 800 950 38 25 9.7
801 – 850 1000 25 40 10.0
851 – 900 1050 21 50 10.5
901 – 950 960 16 60 9.5
≥ 951 1000 10 100 9.9
TOTAL 8959 1268 7.1 100
• Score distribution is obtained by applying the score to the development sample
• Gives us a prediction for new applicants falling into a given score range
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 30
Building a scorecard - the score distribution
Score Band # Goods # Bads GB Odds % Applicants
≤ 400 500 500 1 9.8
401 – 550 700 350 2 10.3
551 – 650 815 163 5 9.6
651 – 700 1008 84 12 10.7
701 – 750 976 61 16 10.1
751 - 800 950 38 25 9.7
801 – 850 1000 25 40 10.0
851 – 900 1050 21 50 10.5
901 – 950 960 16 60 9.5
≥ 951 1000 10 100 9.9
TOTAL 8959 1268 7.1 100
REJECT
REFER
ACCEPT
ACCEPT WITH X-
SELL
Score + Policy Rules + Terms of Business = Strategy
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 31
Agenda
Some basic themes
Analytics and the customer life cycle
The role of scoring
Building a scorecard
Using scoring systems
Risk management infrastructure
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 32
Implementation – the Business Rules Engine
Deployed in:- Origination Application processing Portfolio Management Customer level
decisioning Collections Authorisations Intelligent Messaging Event Management Basel II Stress testing …..
Data
Rules execution(Decision Agent)
Rules execution(Decision Agent)
Rules Definition(Strategy Design Studio)Rules Definition(Strategy Design Studio)
Results
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 33
Implement final decision
Get policy decision & enrichment
strategy
The unsecured lending origination process
Gather & validate application data
Gather existing customer
information
Invoke enrichment strategy
Get decision & terms of business
Handle referrals and manual procedures
Detect application fraud
A full range of client options and interfaces for channel independence and data accuracy
Online links to gather data about existing relationships and customer behaviour
Business-driven scoring & decision-making
Application screening and data matching
Credit bureau links
Business-driven scoring and decision-making
Comprehensive workflow capabilities and provision of relevant data for users
Automated account set-up. Provision of hand-off files. Letter and e-mail production
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 34
Operational environmentOperational environment
Data ManagerStrategic businessStrategic businessenvironmentenvironment
DecisionDecisionEngineEngine
H O S H O S TT
e.g. Account e.g. Account Management Management
System,System,Authorisation Authorisation
SystemSystemetcetc
Defines Defines Business logic, Business logic, Segmentation, Scorecards, Segmentation, Scorecards, Strategies and Champion Strategies and Champion ChallengerChallenger
RuleDefinition
RuleDefinition
ActiveActiveHistoryHistory
VariablesVariables
ExtractExtract
FeedbackFeedback
ResultsResultsAnalyticalAnalyticalData MartData Mart
ImplementsImplementsBusiness logic, Business logic, Segmentation, Scorecards, Segmentation, Scorecards, Strategies and Champion Strategies and Champion ChallengerChallenger
EvaluationEvaluationOptimisationOptimisationReportingReporting
Strategy ImplementationStrategy Implementation
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 35
Using performance data enables better decisions, but is also more complex to combine all the decision influences to maximise value
Influence due to:• Macro-economics?• Use of intuition?• Misunderstanding?
#35
Beyond scoring - strategy optimisation
There are disadvantages to traditional champion/challenger testing…• The time frame for observing results can be long• It can be hard to design the next step• The result can become a “semi-random walk”...
Time
Value
Champion
Challenger 1
Challenger 2
Challenger 3
Challenger n
Decision strategy “deploy-learn-
deploy” process
Challenger 4
The challenger strategy proven in one time period, may no longer be appropriate for another time period – things change
We want to get there with the first challenger !
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 36
#36
Developments in analytics - strategy optimisation
• Experience and intuition
• Trial and error
Incremental benefitROI
Underlying decision complexity
Manual
XXX
XXX
X XXXX X
XX
XXX
XX X
X
X
Scoring
Elaborate Strategies
• single predictive model e.g. credit risk score
• “Heuristic” cut-offs assigned using good:bad odds
• Segmentation based on predictive model dimensions: e.g. risk and revenue
• “Subjective” judgment used to manage trade-offs
XXXX XX
X XXXXXXX
X XX
XX
XX
X
Optimised Strategies
• Allocates optimal action for each customer within constraints
• Objective, mathematical goal maximisation
The next step…
Most are here
Some organisations are still here
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 37
Stage 1: build the infrastructure
Centralisation of credit decisioning
Set-up of IT tools required to automate credit risk and market management processes and the interaction between front line and back office
Development of decision support tools
Development of credit / marketing databasesAutomate the processes
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 38
Stage 2: fine-tune for performance
Fine customer segmentation based on customer profile, product holding and behavior data
Advanced credit and marketing databases drive increased sophistication in statistical models development
Customer interactions for risk and marketing are proactively initiated at all key points
Strategies are designed at customer-level
Automate the decisions
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 39
Stage 3: optimize for excellence
Infrastructure enables total proactive control of the business – decision analytics becomes a way of life
Risk and marketing strategies are centrally designed based on advanced statistical techniques and drive customer profitability
Decision analytics is well structured and integrated across business functions including risk, marketing, sales, operations, finance
Optimize the decisions
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 40
The Road Map
“a world-class consumer finance company”
How well defined and the processes,
and what is the degree of
automation?
How are credit risk, marketing and finance working together? How
are operational and strategic decisions taken?
How well do staff understand all profit drivers? What is the
degree of expertise in credit scoring and decision science?
How are credit policies and strategies defined,
reviewed and improved?
What credit management tools are used? How
flexible are they? How easy is it for business user to change processes and
strategies?
Processes fully support profit-driven strategy,
and are integrated across functions
Profit-driven organisation
across functions
Ongoing knowledge
improvement
Monthly review of credit strategies.
Champion/challenger a way of life
Full suite of scorecards,
ability to optimize credit
strategies
Processes regularly reviewed and refined.
Little manual intervention
Create strategy review cross-functional team
Education on strategy review process, fully
understanding the use of MIS
Profit driven credit strategy in place and
reviewed regularly
Ability to review and modify
credit strategies ‘on the fly’
Ensure clear assignment of responsibilities for risk management functions
Include all available data into the process. Focus underwriter on
“key” review, not second scorecard
Processes well defined and automated
Credit policy in place
Scorecards in place for all critical
segments, decision engine used to
control terms of business. Generate
key KPI’s
Fine-tune for performance
Optimize for excellence
Tools
Strategy
OrganisationKnowledge
Processes
Build the infrastructure
© Experian Limited 2007. All rights reserved.Confidential and proprietary. 41
Conclusions
It all starts with data
Scorecards are important
Strategy is more important
Implementing the strategy properly is vital
If you don’t monitor you’re wasting you time
Risk management is a never-ending journey
© Experian Limited 2007. All rights reserved. Experian and the marks used herein are service marks or registered trademarks of Experian Limited. Other product and company names mentioned herein may be the trademarks of their respective owners. No part of this copyrighted work may be reproduced, modified, or distributed in any form or manner without the prior written permission of Experian Limited.Confidential and proprietary.
Best practice in data & scoring
Dr Paul RussellDirector Analytical Solutions