Improving PD and LGD models following the changes in the market - - PowerPoint PPT Presentation

▶
improving pd and lgd models following the changes in the
SMART_READER_LITE
LIVE PREVIEW

Improving PD and LGD models following the changes in the market - - PowerPoint PPT Presentation

Dec 19, 2023 266 likes •552 views

Improving PD and LGD models following the changes in the market Wemke van der Weij Marcel den Hollander Wemke.vanderWeij@SNSREAAL.nl Marcel.denHollander@SNSREAAL.nl Credit Scoring Conference 2009 - Edinburgh Agenda Introduction Basel

slide-1
SLIDE 1

Improving PD and LGD models following the changes in the market

Wemke.vanderWeij@SNSREAAL.nl Marcel.denHollander@SNSREAAL.nl Credit Scoring Conference 2009 - Edinburgh

Wemke van der Weij Marcel den Hollander

slide-2
SLIDE 2
  • 2 -

Agenda

  • Introduction
  • Basel II
  • Modelling: Rating
  • Modelling: Level
  • Conclusion
slide-3
SLIDE 3
  • 3 -

Introduction

slide-4
SLIDE 4
  • 4 -

Introduction

  • SNS Bank

– Among the largest banking companies in The Netherlands – Balance sheet total of € 77 billion – 3245 employees (FTEs)

  • Corporate staff: Group Risk Management – Credit Risk Management
slide-5
SLIDE 5
  • 5 -

Credit Risk is real...

slide-6
SLIDE 6
  • 6 -

Managing Credit Risk

Acceptation Scorecard

  • New prospects
  • Not required for Basel II
  • Decision to accept

IN OUT

Behaviour models

  • Current customers
  • Required for Basel II
  • Capital requirements
slide-7
SLIDE 7
  • 7 -

But… not always accurate

Realisation versus estimate

0% 2% 4% 6% 8% 10% 12% 14% 16% 18% 20% 200611 200612 200701 200702 200703 200704 200705 200706 200707 200708 200709 200710 200711 200712

Month Percentage

Realisation Estimate

Note that the figures in the presentation do not correspond to actual data

slide-8
SLIDE 8
  • 8 -

Basel II

slide-9
SLIDE 9
  • 9 -
  • 9 -

Key Measures used in Basel II

General Terminology

  • Default
  • PD: Probability of Default
  • LGD: Loss Given Default
  • EAD: Exposure at Default
  • EL: Expected Loss
  • UL: Unexpected Loss
  • ELT: Economic Loss Term
  • DR: Default Rate
  • RLR: Realised Loss Rate

SNS Terminology

slide-10
SLIDE 10
  • 10 -

Conceptual example of default

Default End of default Period t

EAD recovery NPV(Loss)

RLR = NPVd(Loss) EAD

write-off

slide-11
SLIDE 11
  • 11 -
  • 11 -

Framework

Defaults

Probability of Default model Exposure at Default estimate PD fixed 100% Loss Given Default model LGD Best Estimate model LGD X PD X EAD EL =

Non- Defaults

slide-12
SLIDE 12
  • 12 -

Modelling: Rating

slide-13
SLIDE 13
  • 13 -

Profile Credit risk Client Loan Payment behaviour Product Securities

Risk Factors

slide-14
SLIDE 14
  • 14 -

Clients are categorised in buckets

0,00% 5,00% 10,00% 15,00% 20,00% 25,00% 30,00% 35,00% 1 2 3 4 5 6

  • 5.000

10.000 15.000 20.000 25.000 30.000 35.000 Customers (#) RLR LGD

  • Buckets have strictly increasing estimate (LGD or PD)
  • Sufficient observations needed to create buckets
slide-15
SLIDE 15
  • 15 -

Modelling: Level

slide-16
SLIDE 16
  • 16 -

Scoring in pools versus estimated value

Score for each client based on the characteristics Score are categorized in risk classes (buckets) Each bucket gets an estimated value for the risk Client and loan characteristics

slide-17
SLIDE 17
  • 17 -

Estimated values

Example PD pools 1 0.01 % 2 0.05 % 3 0.20% 4 1.00% 5 2.00% 6 8.00% 7 15.00% 8 25.00% LGD pools 1 0.02% 2 0.09% 3 0.50% 4 2.10% 5 7.00% 6 13.00% 7 18.00% 8 30.00%

Commonly based on historical data How can we get these values up to date?

slide-18
SLIDE 18
  • 18 -

Calibration of the estimated value

Layers

– Client (1) – Risk buckets (2) – Portfolio (3)

Frequency

– monthly – quarterly – yearly

Average Value Estimated

(1) (2) (3)

slide-19
SLIDE 19
  • 19 -

Realisation matrix (observed in the xth month)

200909 4.4 200908 5.5 3.4 200907 2.3 2.1 5.4 200906 1.4 2.1 4.2 3.4 200905 1.0 1.1 2.6 1.9 2.3 200904 0.7 0.8 1.2 1.9 3.2 1.7 200903 0.3 0.1 0.4 2.1 1.2 4.2 3.4 200902 0.1 0.2 0.6 1.2 0.9 2.2 4.5 3.2 200901 0.3 0.6 0.2 1.0 3.2 2.1 3.4 3.5 200812 0.0 0.1 2.2 0.8 1.2 2.3 4.3 2.3 200811 0.1 0.1 0.0 0.1 0.1 0.4 1.2 0.7 1.2 1.9 2.3 2.3 200801 0.0 0.2 0.1 0.0 0.6 0.3 0.4 1.1 1.3 1.3 4.2 6.2 200712 0.0 0.1 0.2 0.0 0.0 0.2 0.5 0.9 1.5 1.2 3.2 3.4 200711 >24 24 23 22 … 8 7 6 5 4 3 2 1

Period \ month

PD: clients observed in 200902 and in default in the 3rd month LGD: clients in default in 200902 and recovered / lost in the 3rd month Not observable at the period 200909

slide-20
SLIDE 20
  • 20 -

Economic Loss Term

200909 4.4 200908 5.5 3.4 200907 2.3 2.1 5.4 200906 1.4 2.1 4.2 3.4 200905 1.0 1.1 2.6 1.9 2.3 200904 0.7 0.8 1.2 1.9 3.2 1.7 200903 0.3 0.1 0.4 2.1 1.2 4.2 3.4 200902 0.1 0.2 0.6 1.2 0.9 2.2 4.5 3.2 200901 0.3 0.6 0.2 1.0 3.2 2.1 3.4 3.5 200812 0.0 0.1 2.2 0.8 1.2 2.3 4.3 2.3 200811 0.1 0.1 0.0 0.1 0.1 0.4 1.2 0.7 1.2 1.9 2.3 2.3 200801 0.0 0.2 0.1 0.0 0.6 0.3 0.4 1.1 1.3 1.3 4.2 6.2 200712 0.0 0.1 0.2 0.0 0.0 0.2 0.5 0.9 1.5 1.2 3.2 3.4 200711 >24 24 23 22 … 8 7 6 5 4 3 2 1

Period \ month

How to deal with a default with a very long default period Estimate the loss

slide-21
SLIDE 21
  • 21 -

Realisation matrix (observed in the xth month)

200909 4.4 200908 5.5 3.4 200907 2.3 2.1 5.4 200906 1.4 2.1 4.2 3.4 200905 1.0 1.1 2.6 1.9 2.3 200904 0.7 0.8 1.2 1.9 3.2 1.7 200903 0.3 0.1 0.4 2.1 1.2 4.2 3.4 200902 0.1 0.2 0.6 1.2 0.9 2.2 4.5 3.2 200901 0.3 0.6 0.2 1.0 3.2 2.1 3.4 3.5 200812 0.0 0.1 2.2 0.8 1.2 2.3 4.3 2.3 200811 0.1 0.1 0.0 0.1 0.1 0.4 1.2 0.7 1.2 1.9 2.3 2.3 200801 0.0 0.2 0.1 0.0 0.6 0.3 0.4 1.1 1.3 1.3 4.2 6.2 200712 0.0 0.1 0.2 0.0 0.0 0.2 0.5 0.9 1.5 1.2 3.2 3.4 200711 >24 24 23 22 … 8 7 6 5 4 3 2 1

Period \ month

SUM Xt SUM Xt+1 SUM Xt+1 Historic data used for calibration

slide-22
SLIDE 22
  • 22 -

How to use the realisations

  • Linear regression

– a x + b = y – a = 1 and x +b =y ⇒ linear trend taken

  • Moving Average

– 1/n Sum (x) =y ⇒ average over the last n observations

  • Exponential Smoothing

– a y(t) = x(t) + (1- a)y(t-1)

=>weighted moving average

slide-23
SLIDE 23
  • 23 -

Realisation matrix (observed in the xth month)

200909 4.4 200908 5.5 3.4 200907 2.3 2.1 5.4 200906 1.4 2.1 4.2 3.4 200905 1.0 1.1 2.6 1.9 2.3 200904 0.7 0.8 1.2 1.9 3.2 1.7 200903 0.3 0.1 0.4 2.1 1.2 4.2 3.4 200902 0.1 0.2 0.6 1.2 0.9 2.2 4.5 3.2 200901 0.3 0.6 0.2 1.0 3.2 2.1 3.4 3.5 200812 0.0 0.1 2.2 0.8 1.2 2.3 4.3 2.3 200811 0.1 0.1 0.0 0.1 0.1 0.4 1.2 0.7 1.2 1.9 2.3 2.3 200801 0.0 0.2 0.1 0.0 0.6 0.3 0.4 1.1 1.3 1.3 4.2 6.2 200712 0.0 0.1 0.2 0.0 0.0 0.2 0.5 0.9 1.5 1.2 3.2 3.4 200711 >24 24 23 22 … 8 7 6 5 4 3 2 1

Period \ month

Xt Xt+1 Historic data used for calibration

slide-24
SLIDE 24
  • 24 -

Which is the best

( )

∑

=

−

n t t t

z y n

1 2

1 Root mean square error

∑

=

−

n t t t

z y n

1

1

Mean square error

∑

=

−

n t t t t

z z y n

1

1

Mean absolute percentage error

slide-25
SLIDE 25
  • 25 -

Results for moving average (LGD)

slide-26
SLIDE 26
  • 26 -

Results for moving average (LGD)

slide-27
SLIDE 27
  • 27 -

Conclusion

  • Basel II

– guidelines → credit risk models

  • Observed

– Realisations versus estimates

  • Calibration is needed

– Using historical data avoiding the performance period

  • Case study

Remarks

  • ELT
  • Macro economic variables