Date: Fri, 29 Mar 2024 09:02:04 +0100 (CET)
Message-ID: <1073263969.239.1711699324103@vm-confFLEXnet>
Subject: Exported From Confluence
MIME-Version: 1.0
Content-Type: multipart/related;
boundary="----=_Part_238_1817098922.1711699324100"
------=_Part_238_1817098922.1711699324100
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Content-Location: file:///C:/exported.html
The most significant impact on overall bank management was =
caused by the introduction of the Expected Credit Loss approach to reflect =
credit risk in external accounting.
This approach should ensure that a risk provision, which covers the=
embedded credit risk for all individual deals that belong to a specif=
ic segment, is always available.
The extent, to which this risk provision matches with the required risk =
provision, depends on several factors:
- Quality of macroeconomic parameters =E2=80=93 calibration
- Segmentation criteria that are used to identify deals with similar cred=
it risk. Usually limited to a few criteria because of limited processing ca=
pabilities. This results in high risk due to distortions in the ECL calcula=
tion, since the credit risks of unequal risk objects are offset against eac=
h other and no allocation according to their origin is made. Some transacti=
ons are allocated excessively high credit risks, others too little.
- Mathematical approach
An optimised risk provision ensures that, in the future, enough capital =
is available to cover the depreciation of financial assets linked to defaul=
ts. This leads, in parallel, to the right =E2=80=9Crisk-bearing capacity ca=
pital=E2=80=9D and as a result, it leaves the right space for new=
business at the same time.
- Too much risk provisioning reduces the capital in the balance shee=
t, the covering funds in regulatory capital and the capital that can be use=
d for the regulatory capital ratio.
- Too little covering funds ultimately limit the entity in doing new busi=
ness which will have impact on future profit and loss.
In a perfect world, in which risk provision is not used for "cosmetics" =
in the balance sheet and income statement, the target is to predict future =
expected credit losses as precisely as possible.
The analysis of the precision of predictions based on machine learning can be performed by backtesting=
and compared to predictions based on conventional approaches.
An example of this is the comparison for estimated expected credit losse=
s:
Figure: Comparison of out-of-sample pool-level predictions
For both models, the neuronal network and the conventional approach, the=
figure shows the observed amount of credit losses during 5 years on the x-=
axis for each individual deal and the predicted amount of expected credit l=
osses for a 5-year period on the y-axis. The x =3D y line shows the ideal b=
ut hypothetical scenario under which the predicted and the observed number =
of prepayments coincide. It can be seen that the predictions from the n=
euronal network are closer to this ideal line than those from the conventio=
nal model.
The use of machine learning helps to improve the quality of ECL paramete=
rs such as PD, LGD, EAD and macroeconomic parameters. By doing so, the ECL =
at individual deal level will best reflect the future deterioration in cred=
it quality.
------=_Part_238_1817098922.1711699324100
Content-Type: application/octet-stream
Content-Transfer-Encoding: base64
Content-Location: file:///C:/95986c8ec6fb7dc51c64aac3484b0765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------=_Part_238_1817098922.1711699324100--