SlideShare a Scribd company logo
1 of 6
Download to read offline
Low Probability Default – Sovereign Defaults
Chris Cormack and David Kelly, Quant Foundry
Stuck in the Tail
Challenges posed by regulators such as IFRS9 as well as the desire of asset and treasury managers to
improve their portfolio investment decisions and risk indicators for low probability of default portfolios
have led to a desire to improve forecast methods. This note highlights some of the research performed in
our Quant Labs that shows a demonstrable improvement on previous studies.
The problem with low probability defaults such as those witnessed by sovereigns is that by their very
definition, they do not happen very often and also unlike corporate and retail credit there are no more than
two hundred issuers. Traditional statistical techniques that heroically link disparate probability
distributions to create some narrative around contagion are hampered by fragmented market data that is
concentrated in the highly ranked issuers such as G7.
The input data used in these traditional models are a summary of how the network of investors views a
particular credit. It is the edited highlights, an aggregate view of the consequences of individuals across a
number of institutions completing detailed due diligence. The market data also defines a relative statement
or consensus of the risk-return for where the marginal dollar of investment should be applied. This
marginal dollar of risk, for example, drives the over buying and retrenchment of bond investors in external
emerging markets debt.
Governments fail for many reasons, but there is a pattern of behaviour that any analyst would look to see
for history repeating itself. Examples include; material expansion of external debt, autocratic or corrupt
government, low GDP per population, palm tree present on the national flag. OK not the last one although
it was a criterion for a senior credit officer from the 1990s. The key point is that there are a number of
non-market but still measurable attributes that can be combined to automate the due diligence process a
traditional country credit officer would complete.
The advantage of using a model that leverages off a wide set of data and calibrates well to historic market
and downgrade events is that it is much more consistent and avoids officers “going local” and not viewing
how each country sits alongside its peers.
The Quant Foundry Labs division was approached by a Tier 1 client to introduce modelling techniques that
improves the predictability of low probability defaults while reducing the burden on traditional credit risk
management work. We used a combination of traditional subject matter knowledge and AI tools that
together demonstrably provides a more powerful means of assessing events and finding complex
probabilistic dependencies within the data.
The use of more powerful machine learning techniques comes at a challenge of model transparency. To
address this, we have developed a suite of tools to provide insight and explanation into the model choices
and influence of the model inputs. Together the predictive Machine Learning Algorithm and the diagnostic
tools give rise to a powerful model combination that enables both portfolio mangers and regulatory risk
teams to assess the risks from LDPs as a point in time and through the credit cycle.
Quant Foundry Approach
If there was a buzzword hit parade for 2018, AI and ML would certainly be in the top three. There is much
hype even though the use of artificial intelligence has been a topic of conversation for decades – Forbidden
Planet, C3PO, Hal? Massively improved computation and a tsunami of available data has enabled AI and
ML to flourish and powerful tools have been democratised so that anyone with some technical background
can use them.
Our Quant Foundry Labs division have embraced these techniques but also appreciate that they are still
just tools that need to be treated with the same discipline that we now manage pricing and risk models.
We apply the following approach to all of our AI projects: -
Industry Knowledge
Has to start with industry knowledge to understand the problem we have
been asked to solve, articulate the desired outcome, available data,
solution design using a blend of traditional and AI techniques
Implementation
Detailed understanding of how to combine traditional and AI techniques to
build out a solution. Quality checks on gap-filled input set,
appropriateness of feature set, code testing and deployment
Quality Framework
Documentation of solution design and implementation approach,
preparation of input data test, performance results and explanatory
artefacts, articulation of model limitations and points of instability
Model Scope
The goal of our model is to predict the rating transition probability as a point in time forecast and to
leverage this model to forecast rating transitions up to four quarters ahead and beyond to address some of
the challenges of IFRS9. The predictive power of our model lies in the fact that it uses advanced machine
learning techniques to “learn” what is the most probable rating given different economical and financial
indicators. The model is trained and calibrated using a large set of economic and financial historical data
collected across many different countries: -
Classifier
We designed the classifier that given several economic and financial
parameters at a given quarter predicts the rating at that quarter. Several
machine learning algorithms and feature sets has been tested in order to
maximize the classification accuracy.
Forecast Algorithm
We implemented an algorithm that forecast the economic and financial
parameters needed by the classifier to predict the ratings. We explored
both traditional econometric models like ARIMA (Auto Regressive
Integrated Moving Average) models, and more innovative AI techniques
like standard Recurrent Neural Networks and LSTM models (Long Short
Term Memory)
Forward Evolution
Given the feature predictions and uncertainties we simulate possible
evolution paths. Then we run each path through the classifier. This return
a set of rating probability distributions.
Classifier and the Secret Sauce
AI as with all models cannot operate as an island. It is not credible or possible for a model to dredge the
entire universe of data and come up with a Feature Set that drives the algorithm. The secret sauce here is
industry knowledge and an understanding of the dynamics and red flags of government failure. Getting
this step wrong will allow the AI model to adhere to the time-honoured principle of “garbage in – garbage
out”. The definition of the Feature Set that contributes to the performance of the Classifier follows the
following three steps: -
Expert Selection
We included different kind of indicators: economic data, market data and
governance indicators. We looked for historical time series with the
highest available frequencies and time coverage. We put each time-series
of raw data into a coherent and uniform time grid with monthly and
quarterly frequency
Feature Forecasting
We enhanced the predictive power of our model by building additional
features combining/converting the available ones. This included
percentages, ratios, time decay, changes, spreads and basis. We also
subtracted globally co-ordinated trends such as 2008 meltdown
Final Feature Set
We completed several iterative tests to select the best performing set of
features for the model using a set of custom-built explanatory tools to
highlight feature significance and explanatory power.
Feature Set Selection is a very important process in order to enhance the performances of a classifier. A
higher number of features doesn’t necessarily mean higher accuracy and better results, although will
make it slower. Not all the countries have data on all the features; If we want to include more features in
the model we have to keep in mind that this always comes with the cost of dropping some countries for
which not all the necessary features are available. We need to apply judgement to find a compromise.
The exclusion of critical features due to a poor feature selection can introduce significant bias in the
classifier. We noticed that some features are critical for the classification of medium/lower rated
countries but not for high rating countries and vice-versa. We need to be sure that we are including the
most important once across the all range of ratings. We looked at the feature importance score reported
by the classifier after the training phase for feedback on our selection
Gradient Learning Curve
At this point we have historical data from several countries based on the Feature Set as well as the
issuer’s credit rating. We now need to introduce our enhanced gradient boosted algorithm (GB) to
enable us to forecast the future rating of each country. The objective of our chosen approach is to learn
from history to minimise the difference between predicted rating based on historical data and realised
rating, while overcoming considerable variances in the quality of the historical dataset.
GB is an ensemble technique that combines multiple weak learning algorithms that individually are based
on single decision trees, to gain a higher performance in terms of predictive power. The key advantage of
a gradient boosting algorithm lies in the fact that it learns from its errors.
A GB algorithm creates trees sequentially and at each iteration it adds new decisions trees focusing the
attention on the data points misclassified by the previous set of trees. In this way the predictive loss is
iteratively decreased. The process continues until no further improvements can be made. The name
“gradient boosting” refers to the fact that this technique uses a gradient descent algorithm to minimize
the loss when adding new trees.
So, a trained GB model can be described as the aggregation of weak learners, where each added tree has
been optimized. The final node condition of default can be converted into a probability of that event
happening.
We can now provide a probability estimate for each issuer will land on each rating from AAA to D during
each quarter in the coming year and then weights each member of the Feature Set by significance given
to it.
Validate for Stability
At this stage we should be able to claim victory and we can show results that showcase its predictive
power. What we don’t know is how the model will perform going forward, under different conditions.
We need to make sure the model rating output does not flip flap based on small changes in the Feature
Set.
Feature Set Forecast
The feature forecast algorithm consists of a typical principle component transformation of the data and
then apply a auto-regressive technique to create a four quarter evolution of the feature set. We then
assumed that the uncertainties are gaussian and we drew 100 possible new levels of Feature Set and
then reapply our trained GB model to see how the predicted rating change.		
Visualising
In machine learning, one of the biggest challenges is model explanation and interpretability.
Some machine learning techniques are intrinsically more transparent (Naive Bayes, Decision Trees,
Random Forest). Others such as Neural Networks are trickier to decipher in particular understanding the
importance of each member of the Feature Set. Just because a feature is used deeper in the tree it
doesn’t necessarily mean its importance is lower than features used at higher levels We deploy
visualisation tools that gives less importance to features near the “root of the tree” and give higher
credence to those near the leaves. We deploy visualisation algorithm that looks at the average
difference in predictions over all orderings of the features and gives a more consistent result.
Now for the Results
We described how we trained and calibrated each step of our model. During this process we took from
our sample all the data relative to the last available year. We test the predictive performance of the
classifier by considering how well it knows the true features evolution by un-blinding the test data set.
The subsequent confusion matrix is shown where we can compare the predictions made using the true
values of the features and the predicted values of the features. We can see with the high concentration
in the diagonal the overall model accuracy and the enhanced predictive power around transitions
The graph below shows the strength of the predictability of the model for highly rated and thus low
probability default countries and shows impressive performance. For the next phase of this model
development we plan to capture the dynamics of cross-over movements in particular Southern European
members of the Euro that do not control their domestic currency.
Conclusion
The use of a blend of traditional modelling approaches and AI has improved the predictability of low
probability default models where the prevailing data tends to be a challenge. The use of AI demonstrably
provides an efficient way of conducting non-linear regression across historical data that normal
distribution mapping techniques fail.
The critical element of this exercise is the need industry knowledge of what are the key drivers of a
typical government default and the understanding of how these risk factors interplay in the choice of the
gradient AI model. Testing the model stability is central to any development and we certainly take that
approach. Finally, the methods used to visualise the results are integral to the methodology stack for this
type of model and needs to be included in any validation to make sure the recipients understand what is
going on under the hood when making risk decisions.
At the Quant Foundry, we are very excited by this approach as the results are a step improvement in
what has gone before, and we look forward to discussing this with our collaborators in the data vendor
world as well those that address this challenge in the banks.
The Quant Foundry
The Quant Foundry has been set up by Chris Cormack and David Kelly to provide professional consulting
services, quantitative team augmentation services, software design and development as well as mathematical,
social science and scientific research. Our research division – Quant Labs - includes the design and development
of deep-learning algorithms and Artificial Intelligence models across multiple industrial sectors.
Chris Cormack Delivery Partner chris.cormack@quantfoundry.com
David Kelly Quality Assurance Partner david.kelly@quantfoundry.com

More Related Content

What's hot

Credit Audit's Use of Data Analytics in Examining Consumer Loan Portfolios
Credit Audit's Use of Data Analytics in Examining Consumer Loan PortfoliosCredit Audit's Use of Data Analytics in Examining Consumer Loan Portfolios
Credit Audit's Use of Data Analytics in Examining Consumer Loan PortfoliosJacob Kosoff
 
Enterprise risk management
Enterprise risk managementEnterprise risk management
Enterprise risk managementMetricStream Inc
 
Recognition of information value
Recognition of information valueRecognition of information value
Recognition of information valueMark Albala
 
8 rajib chakravorty risk
8 rajib chakravorty risk8 rajib chakravorty risk
8 rajib chakravorty riskCCR-interactive
 
Understanding and validating the uses of machine learning models
Understanding and validating the uses of machine learning modelsUnderstanding and validating the uses of machine learning models
Understanding and validating the uses of machine learning modelsJacob Kosoff
 
Impact of Recent Supervisory Guidance on Capital Planning
Impact of Recent Supervisory Guidance on Capital PlanningImpact of Recent Supervisory Guidance on Capital Planning
Impact of Recent Supervisory Guidance on Capital PlanningJacob Kosoff
 
Data Science by Chappuis Halder & Co.
Data Science by Chappuis Halder & Co.Data Science by Chappuis Halder & Co.
Data Science by Chappuis Halder & Co.Genest Benoit
 
Creating a Unified Data Strategy for Risk-Adjusted Payments
Creating a Unified Data Strategy for Risk-Adjusted PaymentsCreating a Unified Data Strategy for Risk-Adjusted Payments
Creating a Unified Data Strategy for Risk-Adjusted PaymentsCognizant
 
Optimizing IT Operations with Natural Language Processing
Optimizing IT Operations with Natural Language ProcessingOptimizing IT Operations with Natural Language Processing
Optimizing IT Operations with Natural Language ProcessingCognizant
 
Gamma Advisory Services 2014/03
Gamma Advisory Services 2014/03Gamma Advisory Services 2014/03
Gamma Advisory Services 2014/03Pravin Shirname
 
Cognitivo - Tackling the enterprise data quality challenge
Cognitivo - Tackling the enterprise data quality challengeCognitivo - Tackling the enterprise data quality challenge
Cognitivo - Tackling the enterprise data quality challengeAlan Hsiao
 
Constructing Private Asset Benchmarks
Constructing Private Asset BenchmarksConstructing Private Asset Benchmarks
Constructing Private Asset BenchmarksQuantUniversity
 
Frost&Sullivan Report: Business Analytics
Frost&Sullivan Report: Business Analytics Frost&Sullivan Report: Business Analytics
Frost&Sullivan Report: Business Analytics Judy Misbin
 
PARTNERS 2014 - Dr. Stefan Schwarz - Money for Nothing
PARTNERS 2014 - Dr. Stefan Schwarz - Money for NothingPARTNERS 2014 - Dr. Stefan Schwarz - Money for Nothing
PARTNERS 2014 - Dr. Stefan Schwarz - Money for NothingStefan Schwarz
 
Machine Learning Interpretability
Machine Learning InterpretabilityMachine Learning Interpretability
Machine Learning InterpretabilityQuantUniversity
 
What we do; predictive and prescriptive analytics
What we do; predictive and prescriptive analyticsWhat we do; predictive and prescriptive analytics
What we do; predictive and prescriptive analyticsWeibull AS
 
FastTrack Analytics for Insurance
FastTrack Analytics for InsuranceFastTrack Analytics for Insurance
FastTrack Analytics for InsuranceEdgewater
 
Enablers for Maturing your S&OP Processes, SherTrack
Enablers for Maturing your S&OP Processes, SherTrackEnablers for Maturing your S&OP Processes, SherTrack
Enablers for Maturing your S&OP Processes, SherTrackInnovation Enterprise
 

What's hot (20)

Credit Audit's Use of Data Analytics in Examining Consumer Loan Portfolios
Credit Audit's Use of Data Analytics in Examining Consumer Loan PortfoliosCredit Audit's Use of Data Analytics in Examining Consumer Loan Portfolios
Credit Audit's Use of Data Analytics in Examining Consumer Loan Portfolios
 
Enterprise risk management
Enterprise risk managementEnterprise risk management
Enterprise risk management
 
Risk mgmt-analysis-wp-326822
Risk mgmt-analysis-wp-326822Risk mgmt-analysis-wp-326822
Risk mgmt-analysis-wp-326822
 
Recognition of information value
Recognition of information valueRecognition of information value
Recognition of information value
 
8 rajib chakravorty risk
8 rajib chakravorty risk8 rajib chakravorty risk
8 rajib chakravorty risk
 
Understanding and validating the uses of machine learning models
Understanding and validating the uses of machine learning modelsUnderstanding and validating the uses of machine learning models
Understanding and validating the uses of machine learning models
 
Impact of Recent Supervisory Guidance on Capital Planning
Impact of Recent Supervisory Guidance on Capital PlanningImpact of Recent Supervisory Guidance on Capital Planning
Impact of Recent Supervisory Guidance on Capital Planning
 
Data Science by Chappuis Halder & Co.
Data Science by Chappuis Halder & Co.Data Science by Chappuis Halder & Co.
Data Science by Chappuis Halder & Co.
 
Creating a Unified Data Strategy for Risk-Adjusted Payments
Creating a Unified Data Strategy for Risk-Adjusted PaymentsCreating a Unified Data Strategy for Risk-Adjusted Payments
Creating a Unified Data Strategy for Risk-Adjusted Payments
 
Optimizing IT Operations with Natural Language Processing
Optimizing IT Operations with Natural Language ProcessingOptimizing IT Operations with Natural Language Processing
Optimizing IT Operations with Natural Language Processing
 
Predictive analytics 2025_br
Predictive analytics 2025_brPredictive analytics 2025_br
Predictive analytics 2025_br
 
Gamma Advisory Services 2014/03
Gamma Advisory Services 2014/03Gamma Advisory Services 2014/03
Gamma Advisory Services 2014/03
 
Cognitivo - Tackling the enterprise data quality challenge
Cognitivo - Tackling the enterprise data quality challengeCognitivo - Tackling the enterprise data quality challenge
Cognitivo - Tackling the enterprise data quality challenge
 
Constructing Private Asset Benchmarks
Constructing Private Asset BenchmarksConstructing Private Asset Benchmarks
Constructing Private Asset Benchmarks
 
Frost&Sullivan Report: Business Analytics
Frost&Sullivan Report: Business Analytics Frost&Sullivan Report: Business Analytics
Frost&Sullivan Report: Business Analytics
 
PARTNERS 2014 - Dr. Stefan Schwarz - Money for Nothing
PARTNERS 2014 - Dr. Stefan Schwarz - Money for NothingPARTNERS 2014 - Dr. Stefan Schwarz - Money for Nothing
PARTNERS 2014 - Dr. Stefan Schwarz - Money for Nothing
 
Machine Learning Interpretability
Machine Learning InterpretabilityMachine Learning Interpretability
Machine Learning Interpretability
 
What we do; predictive and prescriptive analytics
What we do; predictive and prescriptive analyticsWhat we do; predictive and prescriptive analytics
What we do; predictive and prescriptive analytics
 
FastTrack Analytics for Insurance
FastTrack Analytics for InsuranceFastTrack Analytics for Insurance
FastTrack Analytics for Insurance
 
Enablers for Maturing your S&OP Processes, SherTrack
Enablers for Maturing your S&OP Processes, SherTrackEnablers for Maturing your S&OP Processes, SherTrack
Enablers for Maturing your S&OP Processes, SherTrack
 

Similar to Low Probability Sovereign Default Prediction

Keys to extract value from the data analytics life cycle
Keys to extract value from the data analytics life cycleKeys to extract value from the data analytics life cycle
Keys to extract value from the data analytics life cycleGrant Thornton LLP
 
Documentation on bigmarket copy
Documentation on bigmarket   copyDocumentation on bigmarket   copy
Documentation on bigmarket copyswamypotharaveni
 
SD Basel process automation seminar presentation
SD Basel process automation seminar presentationSD Basel process automation seminar presentation
SD Basel process automation seminar presentationsarojkdas
 
MACHINE LEARNING CLASSIFIERS TO ANALYZE CREDIT RISK
MACHINE LEARNING CLASSIFIERS TO ANALYZE CREDIT RISKMACHINE LEARNING CLASSIFIERS TO ANALYZE CREDIT RISK
MACHINE LEARNING CLASSIFIERS TO ANALYZE CREDIT RISKIRJET Journal
 
Risk dk
Risk dkRisk dk
Risk dkdkocis
 
Stock Market Trends Prediction after Earning Release.pptx
Stock Market Trends Prediction after Earning Release.pptxStock Market Trends Prediction after Earning Release.pptx
Stock Market Trends Prediction after Earning Release.pptxChen Qian
 
Hedge Fund case study solution - Credit default swaps execution system and Gr...
Hedge Fund case study solution - Credit default swaps execution system and Gr...Hedge Fund case study solution - Credit default swaps execution system and Gr...
Hedge Fund case study solution - Credit default swaps execution system and Gr...Naveen Kumar
 
Analytics and Information Architecture
Analytics and Information ArchitectureAnalytics and Information Architecture
Analytics and Information ArchitectureWilliam McKnight
 
IRJET- Financial Analysis using Data Mining
IRJET- Financial Analysis using Data MiningIRJET- Financial Analysis using Data Mining
IRJET- Financial Analysis using Data MiningIRJET Journal
 
UX STRAT USA 2021: Sönke Rohde, Salesforce
UX STRAT USA 2021: Sönke Rohde, SalesforceUX STRAT USA 2021: Sönke Rohde, Salesforce
UX STRAT USA 2021: Sönke Rohde, SalesforceUX STRAT
 
Data analytics - Alteryx Spotlight.pdf
Data analytics - Alteryx Spotlight.pdfData analytics - Alteryx Spotlight.pdf
Data analytics - Alteryx Spotlight.pdfssuser43b9f8
 
Sergio Juarez, Elemica – “From Big Data to Value: The Power of Master Data Ma...
Sergio Juarez, Elemica – “From Big Data to Value: The Power of Master Data Ma...Sergio Juarez, Elemica – “From Big Data to Value: The Power of Master Data Ma...
Sergio Juarez, Elemica – “From Big Data to Value: The Power of Master Data Ma...Elemica
 
Taming the regulatory tiger with jwg and smartlogic
Taming the regulatory tiger with jwg and smartlogicTaming the regulatory tiger with jwg and smartlogic
Taming the regulatory tiger with jwg and smartlogicAnn Kelly
 
IMPLEMENTATION OF A DECISION SUPPORT SYSTEM AND BUSINESS INTELLIGENCE ALGORIT...
IMPLEMENTATION OF A DECISION SUPPORT SYSTEM AND BUSINESS INTELLIGENCE ALGORIT...IMPLEMENTATION OF A DECISION SUPPORT SYSTEM AND BUSINESS INTELLIGENCE ALGORIT...
IMPLEMENTATION OF A DECISION SUPPORT SYSTEM AND BUSINESS INTELLIGENCE ALGORIT...ijaia
 
Applied_Data_Science_Presented_by_Yhat
Applied_Data_Science_Presented_by_YhatApplied_Data_Science_Presented_by_Yhat
Applied_Data_Science_Presented_by_YhatCharlie Hecht
 
Pragmatic Approach to Datawarehouse Testing_.docx
Pragmatic Approach to Datawarehouse Testing_.docxPragmatic Approach to Datawarehouse Testing_.docx
Pragmatic Approach to Datawarehouse Testing_.docxshankarmani
 

Similar to Low Probability Sovereign Default Prediction (20)

Keys to extract value from the data analytics life cycle
Keys to extract value from the data analytics life cycleKeys to extract value from the data analytics life cycle
Keys to extract value from the data analytics life cycle
 
Documentation on bigmarket copy
Documentation on bigmarket   copyDocumentation on bigmarket   copy
Documentation on bigmarket copy
 
BA_CEC.pptx
BA_CEC.pptxBA_CEC.pptx
BA_CEC.pptx
 
Data Governance
Data GovernanceData Governance
Data Governance
 
CCAR - Kocis
CCAR - KocisCCAR - Kocis
CCAR - Kocis
 
SD Basel process automation seminar presentation
SD Basel process automation seminar presentationSD Basel process automation seminar presentation
SD Basel process automation seminar presentation
 
MACHINE LEARNING CLASSIFIERS TO ANALYZE CREDIT RISK
MACHINE LEARNING CLASSIFIERS TO ANALYZE CREDIT RISKMACHINE LEARNING CLASSIFIERS TO ANALYZE CREDIT RISK
MACHINE LEARNING CLASSIFIERS TO ANALYZE CREDIT RISK
 
Risk dk
Risk dkRisk dk
Risk dk
 
Stock Market Trends Prediction after Earning Release.pptx
Stock Market Trends Prediction after Earning Release.pptxStock Market Trends Prediction after Earning Release.pptx
Stock Market Trends Prediction after Earning Release.pptx
 
Hedge Fund case study solution - Credit default swaps execution system and Gr...
Hedge Fund case study solution - Credit default swaps execution system and Gr...Hedge Fund case study solution - Credit default swaps execution system and Gr...
Hedge Fund case study solution - Credit default swaps execution system and Gr...
 
Dss project analytics writeup
Dss project analytics writeup Dss project analytics writeup
Dss project analytics writeup
 
Analytics and Information Architecture
Analytics and Information ArchitectureAnalytics and Information Architecture
Analytics and Information Architecture
 
IRJET- Financial Analysis using Data Mining
IRJET- Financial Analysis using Data MiningIRJET- Financial Analysis using Data Mining
IRJET- Financial Analysis using Data Mining
 
UX STRAT USA 2021: Sönke Rohde, Salesforce
UX STRAT USA 2021: Sönke Rohde, SalesforceUX STRAT USA 2021: Sönke Rohde, Salesforce
UX STRAT USA 2021: Sönke Rohde, Salesforce
 
Data analytics - Alteryx Spotlight.pdf
Data analytics - Alteryx Spotlight.pdfData analytics - Alteryx Spotlight.pdf
Data analytics - Alteryx Spotlight.pdf
 
Sergio Juarez, Elemica – “From Big Data to Value: The Power of Master Data Ma...
Sergio Juarez, Elemica – “From Big Data to Value: The Power of Master Data Ma...Sergio Juarez, Elemica – “From Big Data to Value: The Power of Master Data Ma...
Sergio Juarez, Elemica – “From Big Data to Value: The Power of Master Data Ma...
 
Taming the regulatory tiger with jwg and smartlogic
Taming the regulatory tiger with jwg and smartlogicTaming the regulatory tiger with jwg and smartlogic
Taming the regulatory tiger with jwg and smartlogic
 
IMPLEMENTATION OF A DECISION SUPPORT SYSTEM AND BUSINESS INTELLIGENCE ALGORIT...
IMPLEMENTATION OF A DECISION SUPPORT SYSTEM AND BUSINESS INTELLIGENCE ALGORIT...IMPLEMENTATION OF A DECISION SUPPORT SYSTEM AND BUSINESS INTELLIGENCE ALGORIT...
IMPLEMENTATION OF A DECISION SUPPORT SYSTEM AND BUSINESS INTELLIGENCE ALGORIT...
 
Applied_Data_Science_Presented_by_Yhat
Applied_Data_Science_Presented_by_YhatApplied_Data_Science_Presented_by_Yhat
Applied_Data_Science_Presented_by_Yhat
 
Pragmatic Approach to Datawarehouse Testing_.docx
Pragmatic Approach to Datawarehouse Testing_.docxPragmatic Approach to Datawarehouse Testing_.docx
Pragmatic Approach to Datawarehouse Testing_.docx
 

Recently uploaded

Dharavi Russian callg Girls, { 09892124323 } || Call Girl In Mumbai ...
Dharavi Russian callg Girls, { 09892124323 } || Call Girl In Mumbai ...Dharavi Russian callg Girls, { 09892124323 } || Call Girl In Mumbai ...
Dharavi Russian callg Girls, { 09892124323 } || Call Girl In Mumbai ...Pooja Nehwal
 
fca-bsps-decision-letter-redacted (1).pdf
fca-bsps-decision-letter-redacted (1).pdffca-bsps-decision-letter-redacted (1).pdf
fca-bsps-decision-letter-redacted (1).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
 
Independent Call Girl Number in Kurla Mumbai📲 Pooja Nehwal 9892124323 💞 Full ...
Independent Call Girl Number in Kurla Mumbai📲 Pooja Nehwal 9892124323 💞 Full ...Independent Call Girl Number in Kurla Mumbai📲 Pooja Nehwal 9892124323 💞 Full ...
Independent Call Girl Number in Kurla Mumbai📲 Pooja Nehwal 9892124323 💞 Full ...Pooja Nehwal
 
VVIP Pune Call Girls Katraj (7001035870) Pune Escorts Nearby with Complete Sa...
VVIP Pune Call Girls Katraj (7001035870) Pune Escorts Nearby with Complete Sa...VVIP Pune Call Girls Katraj (7001035870) Pune Escorts Nearby with Complete Sa...
VVIP Pune Call Girls Katraj (7001035870) Pune Escorts Nearby with Complete Sa...Call Girls in Nagpur High Profile
 
VIP Call Girls in Saharanpur Aarohi 8250192130 Independent Escort Service Sah...
VIP Call Girls in Saharanpur Aarohi 8250192130 Independent Escort Service Sah...VIP Call Girls in Saharanpur Aarohi 8250192130 Independent Escort Service Sah...
VIP Call Girls in Saharanpur Aarohi 8250192130 Independent Escort Service Sah...Suhani Kapoor
 
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
 
VIP Kolkata Call Girl Serampore 👉 8250192130 Available With Room
VIP Kolkata Call Girl Serampore 👉 8250192130  Available With RoomVIP Kolkata Call Girl Serampore 👉 8250192130  Available With Room
VIP Kolkata Call Girl Serampore 👉 8250192130 Available With Roomdivyansh0kumar0
 
Log your LOA pain with Pension Lab's brilliant campaign
Log your LOA pain with Pension Lab's brilliant campaignLog your LOA pain with Pension Lab's brilliant campaign
Log your LOA pain with Pension Lab's brilliant campaignHenry Tapper
 
How Automation is Driving Efficiency Through the Last Mile of Reporting
How Automation is Driving Efficiency Through the Last Mile of ReportingHow Automation is Driving Efficiency Through the Last Mile of Reporting
How Automation is Driving Efficiency Through the Last Mile of ReportingAggregage
 
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
 
20240417-Calibre-April-2024-Investor-Presentation.pdf
20240417-Calibre-April-2024-Investor-Presentation.pdf20240417-Calibre-April-2024-Investor-Presentation.pdf
20240417-Calibre-April-2024-Investor-Presentation.pdfAdnet Communications
 
Q3 2024 Earnings Conference Call and Webcast Slides
Q3 2024 Earnings Conference Call and Webcast SlidesQ3 2024 Earnings Conference Call and Webcast Slides
Q3 2024 Earnings Conference Call and Webcast SlidesMarketing847413
 
New dynamic economic model with a digital footprint | European Business Review
New dynamic economic model with a digital footprint | European Business ReviewNew dynamic economic model with a digital footprint | European Business Review
New dynamic economic model with a digital footprint | European Business ReviewAntonis Zairis
 
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
 
20240429 Calibre April 2024 Investor Presentation.pdf
20240429 Calibre April 2024 Investor Presentation.pdf20240429 Calibre April 2024 Investor Presentation.pdf
20240429 Calibre April 2024 Investor Presentation.pdfAdnet Communications
 

Recently uploaded (20)

Dharavi Russian callg Girls, { 09892124323 } || Call Girl In Mumbai ...
Dharavi Russian callg Girls, { 09892124323 } || Call Girl In Mumbai ...Dharavi Russian callg Girls, { 09892124323 } || Call Girl In Mumbai ...
Dharavi Russian callg Girls, { 09892124323 } || Call Girl In Mumbai ...
 
fca-bsps-decision-letter-redacted (1).pdf
fca-bsps-decision-letter-redacted (1).pdffca-bsps-decision-letter-redacted (1).pdf
fca-bsps-decision-letter-redacted (1).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
 
Independent Call Girl Number in Kurla Mumbai📲 Pooja Nehwal 9892124323 💞 Full ...
Independent Call Girl Number in Kurla Mumbai📲 Pooja Nehwal 9892124323 💞 Full ...Independent Call Girl Number in Kurla Mumbai📲 Pooja Nehwal 9892124323 💞 Full ...
Independent Call Girl Number in Kurla Mumbai📲 Pooja Nehwal 9892124323 💞 Full ...
 
Veritas Interim Report 1 January–31 March 2024
Veritas Interim Report 1 January–31 March 2024Veritas Interim Report 1 January–31 March 2024
Veritas Interim Report 1 January–31 March 2024
 
VVIP Pune Call Girls Katraj (7001035870) Pune Escorts Nearby with Complete Sa...
VVIP Pune Call Girls Katraj (7001035870) Pune Escorts Nearby with Complete Sa...VVIP Pune Call Girls Katraj (7001035870) Pune Escorts Nearby with Complete Sa...
VVIP Pune Call Girls Katraj (7001035870) Pune Escorts Nearby with Complete Sa...
 
VIP Call Girls in Saharanpur Aarohi 8250192130 Independent Escort Service Sah...
VIP Call Girls in Saharanpur Aarohi 8250192130 Independent Escort Service Sah...VIP Call Girls in Saharanpur Aarohi 8250192130 Independent Escort Service Sah...
VIP Call Girls in Saharanpur Aarohi 8250192130 Independent Escort Service Sah...
 
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
 
VIP Kolkata Call Girl Serampore 👉 8250192130 Available With Room
VIP Kolkata Call Girl Serampore 👉 8250192130  Available With RoomVIP Kolkata Call Girl Serampore 👉 8250192130  Available With Room
VIP Kolkata Call Girl Serampore 👉 8250192130 Available With Room
 
Log your LOA pain with Pension Lab's brilliant campaign
Log your LOA pain with Pension Lab's brilliant campaignLog your LOA pain with Pension Lab's brilliant campaign
Log your LOA pain with Pension Lab's brilliant campaign
 
How Automation is Driving Efficiency Through the Last Mile of Reporting
How Automation is Driving Efficiency Through the Last Mile of ReportingHow Automation is Driving Efficiency Through the Last Mile of Reporting
How Automation is Driving Efficiency Through the Last Mile of Reporting
 
🔝+919953056974 🔝young Delhi Escort service Pusa Road
🔝+919953056974 🔝young Delhi Escort service Pusa Road🔝+919953056974 🔝young Delhi Escort service Pusa Road
🔝+919953056974 🔝young Delhi Escort service Pusa Road
 
Commercial Bank Economic Capsule - April 2024
Commercial Bank Economic Capsule - April 2024Commercial Bank Economic Capsule - April 2024
Commercial Bank Economic Capsule - April 2024
 
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
 
20240417-Calibre-April-2024-Investor-Presentation.pdf
20240417-Calibre-April-2024-Investor-Presentation.pdf20240417-Calibre-April-2024-Investor-Presentation.pdf
20240417-Calibre-April-2024-Investor-Presentation.pdf
 
Monthly Economic Monitoring of Ukraine No 231, April 2024
Monthly Economic Monitoring of Ukraine No 231, April 2024Monthly Economic Monitoring of Ukraine No 231, April 2024
Monthly Economic Monitoring of Ukraine No 231, April 2024
 
Q3 2024 Earnings Conference Call and Webcast Slides
Q3 2024 Earnings Conference Call and Webcast SlidesQ3 2024 Earnings Conference Call and Webcast Slides
Q3 2024 Earnings Conference Call and Webcast Slides
 
New dynamic economic model with a digital footprint | European Business Review
New dynamic economic model with a digital footprint | European Business ReviewNew dynamic economic model with a digital footprint | European Business Review
New dynamic economic model with a digital footprint | European Business Review
 
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
 
20240429 Calibre April 2024 Investor Presentation.pdf
20240429 Calibre April 2024 Investor Presentation.pdf20240429 Calibre April 2024 Investor Presentation.pdf
20240429 Calibre April 2024 Investor Presentation.pdf
 

Low Probability Sovereign Default Prediction

  • 1. Low Probability Default – Sovereign Defaults Chris Cormack and David Kelly, Quant Foundry Stuck in the Tail Challenges posed by regulators such as IFRS9 as well as the desire of asset and treasury managers to improve their portfolio investment decisions and risk indicators for low probability of default portfolios have led to a desire to improve forecast methods. This note highlights some of the research performed in our Quant Labs that shows a demonstrable improvement on previous studies. The problem with low probability defaults such as those witnessed by sovereigns is that by their very definition, they do not happen very often and also unlike corporate and retail credit there are no more than two hundred issuers. Traditional statistical techniques that heroically link disparate probability distributions to create some narrative around contagion are hampered by fragmented market data that is concentrated in the highly ranked issuers such as G7. The input data used in these traditional models are a summary of how the network of investors views a particular credit. It is the edited highlights, an aggregate view of the consequences of individuals across a number of institutions completing detailed due diligence. The market data also defines a relative statement or consensus of the risk-return for where the marginal dollar of investment should be applied. This marginal dollar of risk, for example, drives the over buying and retrenchment of bond investors in external emerging markets debt. Governments fail for many reasons, but there is a pattern of behaviour that any analyst would look to see for history repeating itself. Examples include; material expansion of external debt, autocratic or corrupt government, low GDP per population, palm tree present on the national flag. OK not the last one although it was a criterion for a senior credit officer from the 1990s. The key point is that there are a number of non-market but still measurable attributes that can be combined to automate the due diligence process a traditional country credit officer would complete. The advantage of using a model that leverages off a wide set of data and calibrates well to historic market and downgrade events is that it is much more consistent and avoids officers “going local” and not viewing how each country sits alongside its peers. The Quant Foundry Labs division was approached by a Tier 1 client to introduce modelling techniques that improves the predictability of low probability defaults while reducing the burden on traditional credit risk management work. We used a combination of traditional subject matter knowledge and AI tools that together demonstrably provides a more powerful means of assessing events and finding complex probabilistic dependencies within the data. The use of more powerful machine learning techniques comes at a challenge of model transparency. To address this, we have developed a suite of tools to provide insight and explanation into the model choices and influence of the model inputs. Together the predictive Machine Learning Algorithm and the diagnostic tools give rise to a powerful model combination that enables both portfolio mangers and regulatory risk teams to assess the risks from LDPs as a point in time and through the credit cycle.
  • 2. Quant Foundry Approach If there was a buzzword hit parade for 2018, AI and ML would certainly be in the top three. There is much hype even though the use of artificial intelligence has been a topic of conversation for decades – Forbidden Planet, C3PO, Hal? Massively improved computation and a tsunami of available data has enabled AI and ML to flourish and powerful tools have been democratised so that anyone with some technical background can use them. Our Quant Foundry Labs division have embraced these techniques but also appreciate that they are still just tools that need to be treated with the same discipline that we now manage pricing and risk models. We apply the following approach to all of our AI projects: - Industry Knowledge Has to start with industry knowledge to understand the problem we have been asked to solve, articulate the desired outcome, available data, solution design using a blend of traditional and AI techniques Implementation Detailed understanding of how to combine traditional and AI techniques to build out a solution. Quality checks on gap-filled input set, appropriateness of feature set, code testing and deployment Quality Framework Documentation of solution design and implementation approach, preparation of input data test, performance results and explanatory artefacts, articulation of model limitations and points of instability Model Scope The goal of our model is to predict the rating transition probability as a point in time forecast and to leverage this model to forecast rating transitions up to four quarters ahead and beyond to address some of the challenges of IFRS9. The predictive power of our model lies in the fact that it uses advanced machine learning techniques to “learn” what is the most probable rating given different economical and financial indicators. The model is trained and calibrated using a large set of economic and financial historical data collected across many different countries: - Classifier We designed the classifier that given several economic and financial parameters at a given quarter predicts the rating at that quarter. Several machine learning algorithms and feature sets has been tested in order to maximize the classification accuracy. Forecast Algorithm We implemented an algorithm that forecast the economic and financial parameters needed by the classifier to predict the ratings. We explored both traditional econometric models like ARIMA (Auto Regressive Integrated Moving Average) models, and more innovative AI techniques like standard Recurrent Neural Networks and LSTM models (Long Short Term Memory)
  • 3. Forward Evolution Given the feature predictions and uncertainties we simulate possible evolution paths. Then we run each path through the classifier. This return a set of rating probability distributions. Classifier and the Secret Sauce AI as with all models cannot operate as an island. It is not credible or possible for a model to dredge the entire universe of data and come up with a Feature Set that drives the algorithm. The secret sauce here is industry knowledge and an understanding of the dynamics and red flags of government failure. Getting this step wrong will allow the AI model to adhere to the time-honoured principle of “garbage in – garbage out”. The definition of the Feature Set that contributes to the performance of the Classifier follows the following three steps: - Expert Selection We included different kind of indicators: economic data, market data and governance indicators. We looked for historical time series with the highest available frequencies and time coverage. We put each time-series of raw data into a coherent and uniform time grid with monthly and quarterly frequency Feature Forecasting We enhanced the predictive power of our model by building additional features combining/converting the available ones. This included percentages, ratios, time decay, changes, spreads and basis. We also subtracted globally co-ordinated trends such as 2008 meltdown Final Feature Set We completed several iterative tests to select the best performing set of features for the model using a set of custom-built explanatory tools to highlight feature significance and explanatory power. Feature Set Selection is a very important process in order to enhance the performances of a classifier. A higher number of features doesn’t necessarily mean higher accuracy and better results, although will make it slower. Not all the countries have data on all the features; If we want to include more features in the model we have to keep in mind that this always comes with the cost of dropping some countries for which not all the necessary features are available. We need to apply judgement to find a compromise. The exclusion of critical features due to a poor feature selection can introduce significant bias in the classifier. We noticed that some features are critical for the classification of medium/lower rated countries but not for high rating countries and vice-versa. We need to be sure that we are including the most important once across the all range of ratings. We looked at the feature importance score reported by the classifier after the training phase for feedback on our selection
  • 4. Gradient Learning Curve At this point we have historical data from several countries based on the Feature Set as well as the issuer’s credit rating. We now need to introduce our enhanced gradient boosted algorithm (GB) to enable us to forecast the future rating of each country. The objective of our chosen approach is to learn from history to minimise the difference between predicted rating based on historical data and realised rating, while overcoming considerable variances in the quality of the historical dataset. GB is an ensemble technique that combines multiple weak learning algorithms that individually are based on single decision trees, to gain a higher performance in terms of predictive power. The key advantage of a gradient boosting algorithm lies in the fact that it learns from its errors. A GB algorithm creates trees sequentially and at each iteration it adds new decisions trees focusing the attention on the data points misclassified by the previous set of trees. In this way the predictive loss is iteratively decreased. The process continues until no further improvements can be made. The name “gradient boosting” refers to the fact that this technique uses a gradient descent algorithm to minimize the loss when adding new trees. So, a trained GB model can be described as the aggregation of weak learners, where each added tree has been optimized. The final node condition of default can be converted into a probability of that event happening. We can now provide a probability estimate for each issuer will land on each rating from AAA to D during each quarter in the coming year and then weights each member of the Feature Set by significance given to it. Validate for Stability At this stage we should be able to claim victory and we can show results that showcase its predictive power. What we don’t know is how the model will perform going forward, under different conditions. We need to make sure the model rating output does not flip flap based on small changes in the Feature Set. Feature Set Forecast The feature forecast algorithm consists of a typical principle component transformation of the data and then apply a auto-regressive technique to create a four quarter evolution of the feature set. We then assumed that the uncertainties are gaussian and we drew 100 possible new levels of Feature Set and then reapply our trained GB model to see how the predicted rating change. Visualising In machine learning, one of the biggest challenges is model explanation and interpretability. Some machine learning techniques are intrinsically more transparent (Naive Bayes, Decision Trees, Random Forest). Others such as Neural Networks are trickier to decipher in particular understanding the importance of each member of the Feature Set. Just because a feature is used deeper in the tree it
  • 5. doesn’t necessarily mean its importance is lower than features used at higher levels We deploy visualisation tools that gives less importance to features near the “root of the tree” and give higher credence to those near the leaves. We deploy visualisation algorithm that looks at the average difference in predictions over all orderings of the features and gives a more consistent result. Now for the Results We described how we trained and calibrated each step of our model. During this process we took from our sample all the data relative to the last available year. We test the predictive performance of the classifier by considering how well it knows the true features evolution by un-blinding the test data set. The subsequent confusion matrix is shown where we can compare the predictions made using the true values of the features and the predicted values of the features. We can see with the high concentration in the diagonal the overall model accuracy and the enhanced predictive power around transitions The graph below shows the strength of the predictability of the model for highly rated and thus low probability default countries and shows impressive performance. For the next phase of this model development we plan to capture the dynamics of cross-over movements in particular Southern European members of the Euro that do not control their domestic currency.
  • 6. Conclusion The use of a blend of traditional modelling approaches and AI has improved the predictability of low probability default models where the prevailing data tends to be a challenge. The use of AI demonstrably provides an efficient way of conducting non-linear regression across historical data that normal distribution mapping techniques fail. The critical element of this exercise is the need industry knowledge of what are the key drivers of a typical government default and the understanding of how these risk factors interplay in the choice of the gradient AI model. Testing the model stability is central to any development and we certainly take that approach. Finally, the methods used to visualise the results are integral to the methodology stack for this type of model and needs to be included in any validation to make sure the recipients understand what is going on under the hood when making risk decisions. At the Quant Foundry, we are very excited by this approach as the results are a step improvement in what has gone before, and we look forward to discussing this with our collaborators in the data vendor world as well those that address this challenge in the banks. The Quant Foundry The Quant Foundry has been set up by Chris Cormack and David Kelly to provide professional consulting services, quantitative team augmentation services, software design and development as well as mathematical, social science and scientific research. Our research division – Quant Labs - includes the design and development of deep-learning algorithms and Artificial Intelligence models across multiple industrial sectors. Chris Cormack Delivery Partner chris.cormack@quantfoundry.com David Kelly Quality Assurance Partner david.kelly@quantfoundry.com