SlideShare a Scribd company logo
Seminario
MATLAB per il Computational Finance
          Milano, March 22nd 2011



Implementazione e test di un
  modello di credit scoring
            Mattia Ciprian, PhD
           CEO @ modeFinance
• modeFinance is one Italian company active in financial consulting and creditworthiness
  research; thanks to its own rating methodology, MORE, modeFinance provides credit rating
  reports on international markets with companies’ business details, creditworthiness
  evaluations, credit limit values, financial strengths & weaknesses analysis.

Mission

• Every day millions of people around the world are wondering what is the real creditworthiness
  of the companies with which they are in business. Every day, these questions remain
  unanswered. modeFinance every day aims to answer these questions in a simple, complete
  and immediate way.

Products

• modeFinance is specialized in the analysis and evaluation of credit risk assessed to every
  company operating in the world and it supplies different products for helping the customer in
  the financial monitoring of their portfolios (dealers, suppliers, clients, partners, vendors,
  competitors, etc)

modeFinance and Mathworks

• modeFinance has been accepted into The MathWorks Connections Program with its product,
  MORE (Multi Objective Rating Evaluation).
                                      www.modefinance.com
3/22/2011                                                                                    2
                                      info@modefinance.com
CREDIT REPORT              STATISTICAL ANALYSIS             MARKET SEARCH             INTERNAL CREDIT RISK
  The companies who would       Public institutions            The companies who                  PLATFORM
  like to monitor:                                             search the best suppliers,   The companies and the
  customers, suppliers and                                     customers, partnerships.     banks who want to use
  competitors                   Research organizations                                      internal data for the credit
                                                                                            risk assessment
                                                               Banks
  Banks, financial consulting   Associations
  companies


  Insurance companies




                                                  www.modefinance.com
3/22/2011                                                                                                                  3
                                                  info@modefinance.com
Delopment and testing of a credit
scoring model
               www.modefinance.com
3/22/2011                             4
               info@modefinance.com
•   The term credit scoring refers to quantitative methods for evaluating the credit
    quality of companies. Credit scoring is a quantitative exercise that is refreshingly
    productive. A good scoring system can save lenders money and time, and can be a
    first-order competitive advantage.
                                                                         (Source: Falkenstein)

•   The credit score is the first step for a rating assessment.




                                                       Good credit score = good rating




Bad credit score = bad rating


                                     www.modefinance.com
3/22/2011                                                                                        5
                                     info@modefinance.com
1. Z-Score Model: the pioneer predictive tool
      1.    Dataset selection
      2.    Ratio definition
      3.    Credit scoring model selection
      4.    Discriminant analysis (in sample – out of sample)
2. Credit scoring models
3. Model development:
      1.    Choosing inputs;
      2.    Transforming inputs;
      3.    Combining transformed inputs;
      4.    PD evaluation
4. Validating techniques
5. Conclusions


                                     www.modefinance.com
3/22/2011                                                       6
                                     info@modefinance.com
•




    7
•                      •


                       •


                       •




•                      •




            www.modefinance.com
3/22/2011                          8
            info@modefinance.com
1. Z-Score Model: the pioneer predictive tool
      1.    Dataset selection
      2.    Ratio definition
      3.    Credit scoring model selection
      4.    Discriminant analysis (in sample – out of sample)
2. Credit scoring models
3. Model development:
      1.    Choosing inputs;
      2.    Transforming inputs;
      3.    Combining transformed inputs;
      4.    PD evaluation
4. Validating techniques
5. Conclusions


                                     www.modefinance.com
3/22/2011                                                       9
                                     info@modefinance.com
www.modefinance.com
3/22/2011                          10
            info@modefinance.com
1. Z-Score Model: the pioneer predictive tool
      1.    Dataset selection
      2.    Ratio definition
      3.    Credit scoring model selection
      4.    Discriminant analysis (in sample – out of sample)
2. Credit scoring models
3. Model development:
      1.    Choosing inputs;
      2.    Transforming inputs;
      3.    Combining transformed inputs;
      4.    PD evaluation
4. Validating techniques
5. Conclusions


                                     www.modefinance.com
3/22/2011                                                       11
                                     info@modefinance.com
Database
                   Validation                   with
                  techniques                 financial
                                              figures




                PD                                   Ratio
            evaluation                             definition



                                  Ratio
                                selection



                           www.modefinance.com
3/22/2011                                                       12
                           info@modefinance.com
•
      –

      –
            •
            •
            •
            •
      –
            •
            •
            •




                www.modefinance.com
3/22/2011                              13
                info@modefinance.com
•
      –
            •
            •
      –

Z = zscore(A);
Dist = pdist(Z,'seuclidean');
Dist2Matrix = squareform(Dist);
Link = linkage(Dist,'ward');
Cluster = cluster(Link,'maxclust',15);
C = cophenet(Link,Dist);
Err = inconsistent(Link);
figure
[H,T,perm]=dendrogram(Link,'colorthreshold','default');
set(H,'LineWidth',2)



      –



                                          www.modefinance.com
3/22/2011                                                        14
                                          info@modefinance.com
It is possible to define thousands of ratios; in order to avoid redundancy, a first
     simplification can be done by eliminating highly correlated variables.


                                            50



                                            45
   c=corrcoef(database);
   figure; pcolor (c); figure(gcf)          40



                                            35



                                            30


By their nature, most ratios are            25


correlated each other. The objective        20

should not be selecting completely          15

uncorrelated factors                        10



                                            5



                                                 5    10    15   20   25   30   35   40   45   50




                                     www.modefinance.com
3/22/2011                                                                                      15
                                     info@modefinance.com
• The selection of the best set of ratios is the first step in the
  development of a credit scoring model. The set should change
  according to the sector in which the companies are active.
  The selection include both statistical approaches and
  analytical reviews.
• Statistical selection tools suggested:
      –     Distribution Analysis;
      –     F-test and t-Student;
      –     Default Frequencies;
      –     CAP plots;
      –     Etc.
• We’ll apply these tools in the following slides to 2 ratios:
      – CAP = (Shareholders Founds)/(Total Assets);
      – STK = (Stocks)/(Total Assets);




                                      www.modefinance.com
3/22/2011                                                        16
                                      info@modefinance.com
Simple Statistical Analysis




                                  www.modefinance.com
3/22/2011                                                17
                                  info@modefinance.com
• Default Frequency
      – The x-axis shows the percentile in which a particular ratio value lies and the y-
        axis shows the default frequency that is observed for firms with ratios in that
        percentile (Moody’s def).
      – The relation between a financial statement ratio and default is generally
        monotonic and “non-linear”

                    CAP                                           STK




                                     www.modefinance.com
3/22/2011                                                                               18
                                     info@modefinance.com
• CAP Plot (Gini Index)
      – The primary performance measure used by academics was measuring the percentage of
        misclassifications. This was calculated based on the percentage of defaulting firms that
        were accepted, and the percentage of non-defaulting firms that were rejected (Type I
        and Type II errors). Essentially, power curves extend this analysis by plotting the
        cumulative percentage of defaults excluded at each possible cut-off point for a given
        model (Source: Moody’s)




                                       www.modefinance.com
3/22/2011                                                                                     19
                                       info@modefinance.com
CAP                          STK




                  www.modefinance.com
3/22/2011                                      20
                  info@modefinance.com
1. Z-Score Model: the pioneer predictive tool
      1.    Dataset selection
      2.    Ratio definition
      3.    Credit scoring model selection
      4.    Discriminant analysis (in sample – out of sample)
2. Credit scoring models
3. Model development:
      1.    Choosing inputs;
      2.    Transforming inputs;
      3.    Combining transformed inputs;
      4.    PD evaluation
4. Validating techniques
5. Conclusions


                                     www.modefinance.com
3/22/2011                                                       21
                                     info@modefinance.com
• Transformation of this sort are essential because financial ratios are highly
  skewed and fat-tailed, which causes a few observations to overly influence
  the output if not transformed. Transformation methods include:
      –     Replacing the ratio with its percentile;
      –     Turning the ratio into a standard Gaussian variable;
      –     Applying a variety of sigmoidal functions;
      –     Using a nonparametric univariate default estimate generated by each variable
                                                                     Source: Eric Falkenstein studies



                   z = (x-mean(x))./std(x);
                   s = 1 ./ (1 + exp(-z));
                   plot(x,s,'o')




                      CAP                                                 STK




                                              www.modefinance.com
3/22/2011                                                                                               22
                                              info@modefinance.com
1. Z-Score Model: the pioneer predictive tool
      1.    Dataset selection
      2.    Ratio definition
      3.    Credit scoring model selection
      4.    Discriminant analysis (in sample – out of sample)
2. Credit scoring models
3. Model development:
      1.    Choosing inputs;
      2.    Transforming inputs;
      3.    Combining transformed inputs;
      4.    PD evaluation
4. Validating techniques
5. Conclusions


                                     www.modefinance.com
3/22/2011                                                       23
                                     info@modefinance.com
•   If you follow the previous suggestions (reliable data and info, default info,
    representative DB, ratio selection, ratio transformation, etc.), doesn’t matter which
    kind of scoring technique you select.
•   You can choose among:
      –     Discriminant analysis
      –     Logit and Probit
      –     Kernel density estimators (e.g. SVM)
      –     Neural Networks
      –     Genetic Algorithms
      –     Etc.

Maximum Likelihood – Logit function
                                                                                           In the training sample T, L is probability
                                                                                           (likelihood) of the observed situation (if the
                                                     π(i) is the probability of            observations are independent)
                                                     observation i being in set B
                                                     or in set G



                              The problem is that the range of π(i) is [0,1] whereas the
                              predictors can take any real value. Therefore the right-
                              hand side is transformed using a monotonous function.




                                                        www.modefinance.com
3/22/2011                                                                                                                          24
                                                        info@modefinance.com
1. Z-Score Model: the pioneer predictive tool
      1.    Dataset selection
      2.    Ratio definition
      3.    Credit scoring model selection
      4.    Discriminant analysis (in sample – out of sample)
2. Credit scoring models
3. Model development:
      1.    Choosing inputs;
      2.    Transforming inputs;
      3.    Combining transformed inputs;
      4.    PD evaluation
4. Validating techniques
5. Conclusions


                                     www.modefinance.com
3/22/2011                                                       25
                                     info@modefinance.com
EBITDA interest coverage ratio

                    ROE Return on equity

                     ROS Return on sales

 Total Shareholders Founds / Total Assets




                                             www.modefinance.com
3/22/2011                                                           26
                                             info@modefinance.com
1. Z-Score Model: the pioneer predictive tool
      1.    Dataset selection
      2.    Ratio definition
      3.    Credit scoring model selection
      4.    Discriminant analysis (in sample – out of sample)
2. Credit scoring models
3. Model development:
      1.    Choosing inputs;
      2.    Transforming inputs;
      3.    Combining transformed inputs;
      4.    PD evaluation
4. Validating techniques
5. Conclusions


                                     www.modefinance.com
3/22/2011                                                       27
                                     info@modefinance.com
www.modefinance.com
3/22/2011                          28
            info@modefinance.com
1. Z-Score Model: the pioneer predictive tool
      1.    Dataset selection
      2.    Ratio definition
      3.    Credit scoring model selection
      4.    Discriminant analysis (in sample – out of sample)
2. Credit scoring models
3. Model development:
      1.    Choosing inputs;
      2.    Transforming inputs;
      3.    Combining transformed inputs;
      4.    PD evaluation
4. Validating techniques
5. Conclusions


                                     www.modefinance.com
3/22/2011                                                       29
                                     info@modefinance.com

More Related Content

What's hot

Loan Default Prediction with Machine Learning
Loan Default Prediction with Machine LearningLoan Default Prediction with Machine Learning
Loan Default Prediction with Machine Learning
Alibaba Cloud
 
Default Prediction & Analysis on Lending Club Loan Data
Default Prediction & Analysis on Lending Club Loan DataDefault Prediction & Analysis on Lending Club Loan Data
Default Prediction & Analysis on Lending Club Loan Data
Deep Borkar
 
Creditscore
CreditscoreCreditscore
Creditscore
kevinlan
 
Logistic regression
Logistic regressionLogistic regression
Logistic regression
Khaled Abd Elaziz
 
Case Study: Loan default prediction
Case Study: Loan default predictionCase Study: Loan default prediction
Case Study: Loan default prediction
ALTEN Calsoft Labs
 
Predictive Modelling
Predictive ModellingPredictive Modelling
Predictive Modelling
Rajib Kumar De
 
Machine learning in credit risk modeling : a James white paper
Machine learning in credit risk modeling : a James white paperMachine learning in credit risk modeling : a James white paper
Machine learning in credit risk modeling : a James white paper
James by CrowdProcess
 
7 steps to Predictive Analytics
7 steps to Predictive Analytics 7 steps to Predictive Analytics
7 steps to Predictive Analytics
Coforge (Erstwhile WHISHWORKS)
 
Predictive analysis and modelling
Predictive analysis and modellingPredictive analysis and modelling
Predictive analysis and modelling
lalit Lalitm7225
 
Credit Risk Management ppt
Credit Risk Management pptCredit Risk Management ppt
Credit Risk Management ppt
Sneha Salian
 
Default Credit Card Prediction
Default Credit Card PredictionDefault Credit Card Prediction
Default Credit Card Prediction
Alexandre Pinto
 
Decision tree for Predictive Modeling
Decision tree for Predictive ModelingDecision tree for Predictive Modeling
Decision tree for Predictive Modeling
Edureka!
 
Loan default prediction with machine language
Loan  default  prediction with  machine  language Loan  default  prediction with  machine  language
Loan default prediction with machine language
Aayush Kumar
 
Predictive Analysis Powerpoint Presentation Slides
Predictive Analysis Powerpoint Presentation SlidesPredictive Analysis Powerpoint Presentation Slides
Predictive Analysis Powerpoint Presentation Slides
SlideTeam
 
Predictive Model for Loan Approval Process using SAS 9.3_M1
Predictive Model for Loan Approval Process using SAS 9.3_M1Predictive Model for Loan Approval Process using SAS 9.3_M1
Predictive Model for Loan Approval Process using SAS 9.3_M1
Akanksha Jain
 
Fraud detection ML
Fraud detection MLFraud detection ML
Fraud detection ML
MaatougSelim
 
Bank churn with Data Science
Bank churn with Data ScienceBank churn with Data Science
Bank churn with Data Science
Carolyn Knight
 
Logistic regression
Logistic regressionLogistic regression
Logistic regression
DrZahid Khan
 
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Simplilearn
 
Jntu credit risk-management
Jntu credit risk-managementJntu credit risk-management
Jntu credit risk-management
ShivaLeela Choudary
 

What's hot (20)

Loan Default Prediction with Machine Learning
Loan Default Prediction with Machine LearningLoan Default Prediction with Machine Learning
Loan Default Prediction with Machine Learning
 
Default Prediction & Analysis on Lending Club Loan Data
Default Prediction & Analysis on Lending Club Loan DataDefault Prediction & Analysis on Lending Club Loan Data
Default Prediction & Analysis on Lending Club Loan Data
 
Creditscore
CreditscoreCreditscore
Creditscore
 
Logistic regression
Logistic regressionLogistic regression
Logistic regression
 
Case Study: Loan default prediction
Case Study: Loan default predictionCase Study: Loan default prediction
Case Study: Loan default prediction
 
Predictive Modelling
Predictive ModellingPredictive Modelling
Predictive Modelling
 
Machine learning in credit risk modeling : a James white paper
Machine learning in credit risk modeling : a James white paperMachine learning in credit risk modeling : a James white paper
Machine learning in credit risk modeling : a James white paper
 
7 steps to Predictive Analytics
7 steps to Predictive Analytics 7 steps to Predictive Analytics
7 steps to Predictive Analytics
 
Predictive analysis and modelling
Predictive analysis and modellingPredictive analysis and modelling
Predictive analysis and modelling
 
Credit Risk Management ppt
Credit Risk Management pptCredit Risk Management ppt
Credit Risk Management ppt
 
Default Credit Card Prediction
Default Credit Card PredictionDefault Credit Card Prediction
Default Credit Card Prediction
 
Decision tree for Predictive Modeling
Decision tree for Predictive ModelingDecision tree for Predictive Modeling
Decision tree for Predictive Modeling
 
Loan default prediction with machine language
Loan  default  prediction with  machine  language Loan  default  prediction with  machine  language
Loan default prediction with machine language
 
Predictive Analysis Powerpoint Presentation Slides
Predictive Analysis Powerpoint Presentation SlidesPredictive Analysis Powerpoint Presentation Slides
Predictive Analysis Powerpoint Presentation Slides
 
Predictive Model for Loan Approval Process using SAS 9.3_M1
Predictive Model for Loan Approval Process using SAS 9.3_M1Predictive Model for Loan Approval Process using SAS 9.3_M1
Predictive Model for Loan Approval Process using SAS 9.3_M1
 
Fraud detection ML
Fraud detection MLFraud detection ML
Fraud detection ML
 
Bank churn with Data Science
Bank churn with Data ScienceBank churn with Data Science
Bank churn with Data Science
 
Logistic regression
Logistic regressionLogistic regression
Logistic regression
 
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
Logistic Regression | Logistic Regression In Python | Machine Learning Algori...
 
Jntu credit risk-management
Jntu credit risk-managementJntu credit risk-management
Jntu credit risk-management
 

Similar to Delopment and testing of a credit scoring model

Applications of Data Science in Banking and Financial sector.pptx
Applications of Data Science in Banking and Financial sector.pptxApplications of Data Science in Banking and Financial sector.pptx
Applications of Data Science in Banking and Financial sector.pptx
karnika21
 
IRJET- Prediction of Credit Risks in Lending Bank Loans
IRJET- Prediction of Credit Risks in Lending Bank LoansIRJET- Prediction of Credit Risks in Lending Bank Loans
IRJET- Prediction of Credit Risks in Lending Bank Loans
IRJET Journal
 
Presentation to SEC Staff: Open Source Alternatives to Credit Ratings
Presentation to SEC Staff: Open Source Alternatives to Credit RatingsPresentation to SEC Staff: Open Source Alternatives to Credit Ratings
Presentation to SEC Staff: Open Source Alternatives to Credit Ratings
Marc Joffe
 
Fractal Labs Capability Set
Fractal Labs Capability SetFractal Labs Capability Set
Fractal Labs Capability Set
Mark Young
 
Tutorial on Advances in Bias-aware Recommendation on the Web @ WSDM 2021
Tutorial on Advances in Bias-aware Recommendation on the Web @ WSDM 2021Tutorial on Advances in Bias-aware Recommendation on the Web @ WSDM 2021
Tutorial on Advances in Bias-aware Recommendation on the Web @ WSDM 2021
Mirko Marras
 
QuantUniversity Fintech Bootcamp Day- 4
QuantUniversity Fintech Bootcamp Day- 4QuantUniversity Fintech Bootcamp Day- 4
QuantUniversity Fintech Bootcamp Day- 4
QuantUniversity
 
Credit appraisal SYSTEM
Credit appraisal SYSTEMCredit appraisal SYSTEM
Credit appraisal SYSTEM
Anil Chaurasiya
 
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
ISPMAIndia
 
Credit risk assessment with imbalanced data sets using SVMs
Credit risk assessment with imbalanced data sets using SVMsCredit risk assessment with imbalanced data sets using SVMs
Credit risk assessment with imbalanced data sets using SVMs
IRJET Journal
 
Jp morgan blockchain bitcoin
Jp morgan blockchain bitcoinJp morgan blockchain bitcoin
Jp morgan blockchain bitcoin
Rein Mahatma
 
Loan approval prediction based on machine learning approach
Loan approval prediction based on machine learning approachLoan approval prediction based on machine learning approach
Loan approval prediction based on machine learning approach
Eslam Nader
 
B510519.pdf
B510519.pdfB510519.pdf
B510519.pdf
aijbm
 
Micro credit process and challenges
Micro credit process and challengesMicro credit process and challenges
Micro credit process and challenges
Pranav Singh
 
Telemarketing prediction project
Telemarketing prediction projectTelemarketing prediction project
Telemarketing prediction project
Learnbay Datascience
 
BANK LOAN PREDICTION USING MACHINE LEARNING
BANK LOAN PREDICTION USING MACHINE LEARNINGBANK LOAN PREDICTION USING MACHINE LEARNING
BANK LOAN PREDICTION USING MACHINE LEARNING
IRJET Journal
 
cgap-it-innovation-series-credit-scoring-2004
cgap-it-innovation-series-credit-scoring-2004cgap-it-innovation-series-credit-scoring-2004
cgap-it-innovation-series-credit-scoring-2004
Dan Salazar
 
When Worlds Collide - Big Data & Web Analytics in 2013 - Jean-Francois Belisle
When Worlds Collide - Big Data & Web Analytics in 2013 - Jean-Francois BelisleWhen Worlds Collide - Big Data & Web Analytics in 2013 - Jean-Francois Belisle
When Worlds Collide - Big Data & Web Analytics in 2013 - Jean-Francois Belisle
Jean-Francois Belisle
 
ComScore Online & Mobile Banking
ComScore Online & Mobile BankingComScore Online & Mobile Banking
ComScore Online & Mobile Banking
Andrei Kamarouski
 
ModelBank2015_Part2_Omnichannel
ModelBank2015_Part2_OmnichannelModelBank2015_Part2_Omnichannel
ModelBank2015_Part2_Omnichannel
Christine Pierson
 
Social media and content ims marketo - sfo 19
Social media and content   ims marketo - sfo 19Social media and content   ims marketo - sfo 19
Social media and content ims marketo - sfo 19
Inbound Marketing Summit
 

Similar to Delopment and testing of a credit scoring model (20)

Applications of Data Science in Banking and Financial sector.pptx
Applications of Data Science in Banking and Financial sector.pptxApplications of Data Science in Banking and Financial sector.pptx
Applications of Data Science in Banking and Financial sector.pptx
 
IRJET- Prediction of Credit Risks in Lending Bank Loans
IRJET- Prediction of Credit Risks in Lending Bank LoansIRJET- Prediction of Credit Risks in Lending Bank Loans
IRJET- Prediction of Credit Risks in Lending Bank Loans
 
Presentation to SEC Staff: Open Source Alternatives to Credit Ratings
Presentation to SEC Staff: Open Source Alternatives to Credit RatingsPresentation to SEC Staff: Open Source Alternatives to Credit Ratings
Presentation to SEC Staff: Open Source Alternatives to Credit Ratings
 
Fractal Labs Capability Set
Fractal Labs Capability SetFractal Labs Capability Set
Fractal Labs Capability Set
 
Tutorial on Advances in Bias-aware Recommendation on the Web @ WSDM 2021
Tutorial on Advances in Bias-aware Recommendation on the Web @ WSDM 2021Tutorial on Advances in Bias-aware Recommendation on the Web @ WSDM 2021
Tutorial on Advances in Bias-aware Recommendation on the Web @ WSDM 2021
 
QuantUniversity Fintech Bootcamp Day- 4
QuantUniversity Fintech Bootcamp Day- 4QuantUniversity Fintech Bootcamp Day- 4
QuantUniversity Fintech Bootcamp Day- 4
 
Credit appraisal SYSTEM
Credit appraisal SYSTEMCredit appraisal SYSTEM
Credit appraisal SYSTEM
 
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
 
Credit risk assessment with imbalanced data sets using SVMs
Credit risk assessment with imbalanced data sets using SVMsCredit risk assessment with imbalanced data sets using SVMs
Credit risk assessment with imbalanced data sets using SVMs
 
Jp morgan blockchain bitcoin
Jp morgan blockchain bitcoinJp morgan blockchain bitcoin
Jp morgan blockchain bitcoin
 
Loan approval prediction based on machine learning approach
Loan approval prediction based on machine learning approachLoan approval prediction based on machine learning approach
Loan approval prediction based on machine learning approach
 
B510519.pdf
B510519.pdfB510519.pdf
B510519.pdf
 
Micro credit process and challenges
Micro credit process and challengesMicro credit process and challenges
Micro credit process and challenges
 
Telemarketing prediction project
Telemarketing prediction projectTelemarketing prediction project
Telemarketing prediction project
 
BANK LOAN PREDICTION USING MACHINE LEARNING
BANK LOAN PREDICTION USING MACHINE LEARNINGBANK LOAN PREDICTION USING MACHINE LEARNING
BANK LOAN PREDICTION USING MACHINE LEARNING
 
cgap-it-innovation-series-credit-scoring-2004
cgap-it-innovation-series-credit-scoring-2004cgap-it-innovation-series-credit-scoring-2004
cgap-it-innovation-series-credit-scoring-2004
 
When Worlds Collide - Big Data & Web Analytics in 2013 - Jean-Francois Belisle
When Worlds Collide - Big Data & Web Analytics in 2013 - Jean-Francois BelisleWhen Worlds Collide - Big Data & Web Analytics in 2013 - Jean-Francois Belisle
When Worlds Collide - Big Data & Web Analytics in 2013 - Jean-Francois Belisle
 
ComScore Online & Mobile Banking
ComScore Online & Mobile BankingComScore Online & Mobile Banking
ComScore Online & Mobile Banking
 
ModelBank2015_Part2_Omnichannel
ModelBank2015_Part2_OmnichannelModelBank2015_Part2_Omnichannel
ModelBank2015_Part2_Omnichannel
 
Social media and content ims marketo - sfo 19
Social media and content   ims marketo - sfo 19Social media and content   ims marketo - sfo 19
Social media and content ims marketo - sfo 19
 

Recently uploaded

Does teamwork really matter? Looking beyond the job posting to understand lab...
Does teamwork really matter? Looking beyond the job posting to understand lab...Does teamwork really matter? Looking beyond the job posting to understand lab...
Does teamwork really matter? Looking beyond the job posting to understand lab...
Labour Market Information Council | Conseil de l’information sur le marché du travail
 
一比一原版美国新罕布什尔大学(unh)毕业证学历认证真实可查
一比一原版美国新罕布什尔大学(unh)毕业证学历认证真实可查一比一原版美国新罕布什尔大学(unh)毕业证学历认证真实可查
一比一原版美国新罕布什尔大学(unh)毕业证学历认证真实可查
taqyea
 
Who Is the Largest Producer of Soybean in India Now.pdf
Who Is the Largest Producer of Soybean in India Now.pdfWho Is the Largest Producer of Soybean in India Now.pdf
Who Is the Largest Producer of Soybean in India Now.pdf
Price Vision
 
2. Elemental Economics - Mineral demand.pdf
2. Elemental Economics - Mineral demand.pdf2. Elemental Economics - Mineral demand.pdf
2. Elemental Economics - Mineral demand.pdf
Neal Brewster
 
1. Elemental Economics - Introduction to mining.pdf
1. Elemental Economics - Introduction to mining.pdf1. Elemental Economics - Introduction to mining.pdf
1. Elemental Economics - Introduction to mining.pdf
Neal Brewster
 
一比一原版(GWU,GW毕业证)加利福尼亚大学|尔湾分校毕业证如何办理
一比一原版(GWU,GW毕业证)加利福尼亚大学|尔湾分校毕业证如何办理一比一原版(GWU,GW毕业证)加利福尼亚大学|尔湾分校毕业证如何办理
一比一原版(GWU,GW毕业证)加利福尼亚大学|尔湾分校毕业证如何办理
obyzuk
 
Independent Study - College of Wooster Research (2023-2024)
Independent Study - College of Wooster Research (2023-2024)Independent Study - College of Wooster Research (2023-2024)
Independent Study - College of Wooster Research (2023-2024)
AntoniaOwensDetwiler
 
Bridging the gap: Online job postings, survey data and the assessment of job ...
Bridging the gap: Online job postings, survey data and the assessment of job ...Bridging the gap: Online job postings, survey data and the assessment of job ...
Bridging the gap: Online job postings, survey data and the assessment of job ...
Labour Market Information Council | Conseil de l’information sur le marché du travail
 
FCCS Basic Accounts Outline and Hierarchy.pptx
FCCS Basic Accounts Outline and Hierarchy.pptxFCCS Basic Accounts Outline and Hierarchy.pptx
FCCS Basic Accounts Outline and Hierarchy.pptx
nalamynandan
 
5 Tips for Creating Standard Financial Reports
5 Tips for Creating Standard Financial Reports5 Tips for Creating Standard Financial Reports
5 Tips for Creating Standard Financial Reports
EasyReports
 
falcon-invoice-discounting-a-premier-investment-platform-for-superior-returns...
falcon-invoice-discounting-a-premier-investment-platform-for-superior-returns...falcon-invoice-discounting-a-premier-investment-platform-for-superior-returns...
falcon-invoice-discounting-a-premier-investment-platform-for-superior-returns...
Falcon Invoice Discounting
 
Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...
Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...
Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...
AntoniaOwensDetwiler
 
一比一原版(UoB毕业证)伯明翰大学毕业证如何办理
一比一原版(UoB毕业证)伯明翰大学毕业证如何办理一比一原版(UoB毕业证)伯明翰大学毕业证如何办理
一比一原版(UoB毕业证)伯明翰大学毕业证如何办理
nexop1
 
快速办理(SMU毕业证书)南卫理公会大学毕业证毕业完成信一模一样
快速办理(SMU毕业证书)南卫理公会大学毕业证毕业完成信一模一样快速办理(SMU毕业证书)南卫理公会大学毕业证毕业完成信一模一样
快速办理(SMU毕业证书)南卫理公会大学毕业证毕业完成信一模一样
5spllj1l
 
一比一原版(UCSB毕业证)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB毕业证)圣芭芭拉分校毕业证如何办理一比一原版(UCSB毕业证)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB毕业证)圣芭芭拉分校毕业证如何办理
bbeucd
 
OAT_RI_Ep20 WeighingTheRisks_May24_Trade Wars.pptx
OAT_RI_Ep20 WeighingTheRisks_May24_Trade Wars.pptxOAT_RI_Ep20 WeighingTheRisks_May24_Trade Wars.pptx
OAT_RI_Ep20 WeighingTheRisks_May24_Trade Wars.pptx
hiddenlevers
 
1:1制作加拿大麦吉尔大学毕业证硕士学历证书原版一模一样
1:1制作加拿大麦吉尔大学毕业证硕士学历证书原版一模一样1:1制作加拿大麦吉尔大学毕业证硕士学历证书原版一模一样
1:1制作加拿大麦吉尔大学毕业证硕士学历证书原版一模一样
qntjwn68
 
Pensions and housing - Pensions PlayPen - 4 June 2024 v3 (1).pdf
Pensions and housing - Pensions PlayPen - 4 June 2024 v3 (1).pdfPensions and housing - Pensions PlayPen - 4 June 2024 v3 (1).pdf
Pensions and housing - Pensions PlayPen - 4 June 2024 v3 (1).pdf
Henry Tapper
 
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...
Donc Test
 
Seminar: Gender Board Diversity through Ownership Networks
Seminar: Gender Board Diversity through Ownership NetworksSeminar: Gender Board Diversity through Ownership Networks
Seminar: Gender Board Diversity through Ownership Networks
GRAPE
 

Recently uploaded (20)

Does teamwork really matter? Looking beyond the job posting to understand lab...
Does teamwork really matter? Looking beyond the job posting to understand lab...Does teamwork really matter? Looking beyond the job posting to understand lab...
Does teamwork really matter? Looking beyond the job posting to understand lab...
 
一比一原版美国新罕布什尔大学(unh)毕业证学历认证真实可查
一比一原版美国新罕布什尔大学(unh)毕业证学历认证真实可查一比一原版美国新罕布什尔大学(unh)毕业证学历认证真实可查
一比一原版美国新罕布什尔大学(unh)毕业证学历认证真实可查
 
Who Is the Largest Producer of Soybean in India Now.pdf
Who Is the Largest Producer of Soybean in India Now.pdfWho Is the Largest Producer of Soybean in India Now.pdf
Who Is the Largest Producer of Soybean in India Now.pdf
 
2. Elemental Economics - Mineral demand.pdf
2. Elemental Economics - Mineral demand.pdf2. Elemental Economics - Mineral demand.pdf
2. Elemental Economics - Mineral demand.pdf
 
1. Elemental Economics - Introduction to mining.pdf
1. Elemental Economics - Introduction to mining.pdf1. Elemental Economics - Introduction to mining.pdf
1. Elemental Economics - Introduction to mining.pdf
 
一比一原版(GWU,GW毕业证)加利福尼亚大学|尔湾分校毕业证如何办理
一比一原版(GWU,GW毕业证)加利福尼亚大学|尔湾分校毕业证如何办理一比一原版(GWU,GW毕业证)加利福尼亚大学|尔湾分校毕业证如何办理
一比一原版(GWU,GW毕业证)加利福尼亚大学|尔湾分校毕业证如何办理
 
Independent Study - College of Wooster Research (2023-2024)
Independent Study - College of Wooster Research (2023-2024)Independent Study - College of Wooster Research (2023-2024)
Independent Study - College of Wooster Research (2023-2024)
 
Bridging the gap: Online job postings, survey data and the assessment of job ...
Bridging the gap: Online job postings, survey data and the assessment of job ...Bridging the gap: Online job postings, survey data and the assessment of job ...
Bridging the gap: Online job postings, survey data and the assessment of job ...
 
FCCS Basic Accounts Outline and Hierarchy.pptx
FCCS Basic Accounts Outline and Hierarchy.pptxFCCS Basic Accounts Outline and Hierarchy.pptx
FCCS Basic Accounts Outline and Hierarchy.pptx
 
5 Tips for Creating Standard Financial Reports
5 Tips for Creating Standard Financial Reports5 Tips for Creating Standard Financial Reports
5 Tips for Creating Standard Financial Reports
 
falcon-invoice-discounting-a-premier-investment-platform-for-superior-returns...
falcon-invoice-discounting-a-premier-investment-platform-for-superior-returns...falcon-invoice-discounting-a-premier-investment-platform-for-superior-returns...
falcon-invoice-discounting-a-premier-investment-platform-for-superior-returns...
 
Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...
Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...
Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...
 
一比一原版(UoB毕业证)伯明翰大学毕业证如何办理
一比一原版(UoB毕业证)伯明翰大学毕业证如何办理一比一原版(UoB毕业证)伯明翰大学毕业证如何办理
一比一原版(UoB毕业证)伯明翰大学毕业证如何办理
 
快速办理(SMU毕业证书)南卫理公会大学毕业证毕业完成信一模一样
快速办理(SMU毕业证书)南卫理公会大学毕业证毕业完成信一模一样快速办理(SMU毕业证书)南卫理公会大学毕业证毕业完成信一模一样
快速办理(SMU毕业证书)南卫理公会大学毕业证毕业完成信一模一样
 
一比一原版(UCSB毕业证)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB毕业证)圣芭芭拉分校毕业证如何办理一比一原版(UCSB毕业证)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB毕业证)圣芭芭拉分校毕业证如何办理
 
OAT_RI_Ep20 WeighingTheRisks_May24_Trade Wars.pptx
OAT_RI_Ep20 WeighingTheRisks_May24_Trade Wars.pptxOAT_RI_Ep20 WeighingTheRisks_May24_Trade Wars.pptx
OAT_RI_Ep20 WeighingTheRisks_May24_Trade Wars.pptx
 
1:1制作加拿大麦吉尔大学毕业证硕士学历证书原版一模一样
1:1制作加拿大麦吉尔大学毕业证硕士学历证书原版一模一样1:1制作加拿大麦吉尔大学毕业证硕士学历证书原版一模一样
1:1制作加拿大麦吉尔大学毕业证硕士学历证书原版一模一样
 
Pensions and housing - Pensions PlayPen - 4 June 2024 v3 (1).pdf
Pensions and housing - Pensions PlayPen - 4 June 2024 v3 (1).pdfPensions and housing - Pensions PlayPen - 4 June 2024 v3 (1).pdf
Pensions and housing - Pensions PlayPen - 4 June 2024 v3 (1).pdf
 
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...
 
Seminar: Gender Board Diversity through Ownership Networks
Seminar: Gender Board Diversity through Ownership NetworksSeminar: Gender Board Diversity through Ownership Networks
Seminar: Gender Board Diversity through Ownership Networks
 

Delopment and testing of a credit scoring model

  • 1. Seminario MATLAB per il Computational Finance Milano, March 22nd 2011 Implementazione e test di un modello di credit scoring Mattia Ciprian, PhD CEO @ modeFinance
  • 2. • modeFinance is one Italian company active in financial consulting and creditworthiness research; thanks to its own rating methodology, MORE, modeFinance provides credit rating reports on international markets with companies’ business details, creditworthiness evaluations, credit limit values, financial strengths & weaknesses analysis. Mission • Every day millions of people around the world are wondering what is the real creditworthiness of the companies with which they are in business. Every day, these questions remain unanswered. modeFinance every day aims to answer these questions in a simple, complete and immediate way. Products • modeFinance is specialized in the analysis and evaluation of credit risk assessed to every company operating in the world and it supplies different products for helping the customer in the financial monitoring of their portfolios (dealers, suppliers, clients, partners, vendors, competitors, etc) modeFinance and Mathworks • modeFinance has been accepted into The MathWorks Connections Program with its product, MORE (Multi Objective Rating Evaluation). www.modefinance.com 3/22/2011 2 info@modefinance.com
  • 3. CREDIT REPORT STATISTICAL ANALYSIS MARKET SEARCH INTERNAL CREDIT RISK The companies who would Public institutions The companies who PLATFORM like to monitor: search the best suppliers, The companies and the customers, suppliers and customers, partnerships. banks who want to use competitors Research organizations internal data for the credit risk assessment Banks Banks, financial consulting Associations companies Insurance companies www.modefinance.com 3/22/2011 3 info@modefinance.com
  • 4. Delopment and testing of a credit scoring model www.modefinance.com 3/22/2011 4 info@modefinance.com
  • 5. The term credit scoring refers to quantitative methods for evaluating the credit quality of companies. Credit scoring is a quantitative exercise that is refreshingly productive. A good scoring system can save lenders money and time, and can be a first-order competitive advantage. (Source: Falkenstein) • The credit score is the first step for a rating assessment. Good credit score = good rating Bad credit score = bad rating www.modefinance.com 3/22/2011 5 info@modefinance.com
  • 6. 1. Z-Score Model: the pioneer predictive tool 1. Dataset selection 2. Ratio definition 3. Credit scoring model selection 4. Discriminant analysis (in sample – out of sample) 2. Credit scoring models 3. Model development: 1. Choosing inputs; 2. Transforming inputs; 3. Combining transformed inputs; 4. PD evaluation 4. Validating techniques 5. Conclusions www.modefinance.com 3/22/2011 6 info@modefinance.com
  • 7. 7
  • 8. • • • • • www.modefinance.com 3/22/2011 8 info@modefinance.com
  • 9. 1. Z-Score Model: the pioneer predictive tool 1. Dataset selection 2. Ratio definition 3. Credit scoring model selection 4. Discriminant analysis (in sample – out of sample) 2. Credit scoring models 3. Model development: 1. Choosing inputs; 2. Transforming inputs; 3. Combining transformed inputs; 4. PD evaluation 4. Validating techniques 5. Conclusions www.modefinance.com 3/22/2011 9 info@modefinance.com
  • 10. www.modefinance.com 3/22/2011 10 info@modefinance.com
  • 11. 1. Z-Score Model: the pioneer predictive tool 1. Dataset selection 2. Ratio definition 3. Credit scoring model selection 4. Discriminant analysis (in sample – out of sample) 2. Credit scoring models 3. Model development: 1. Choosing inputs; 2. Transforming inputs; 3. Combining transformed inputs; 4. PD evaluation 4. Validating techniques 5. Conclusions www.modefinance.com 3/22/2011 11 info@modefinance.com
  • 12. Database Validation with techniques financial figures PD Ratio evaluation definition Ratio selection www.modefinance.com 3/22/2011 12 info@modefinance.com
  • 13. – – • • • • – • • • www.modefinance.com 3/22/2011 13 info@modefinance.com
  • 14. – • • – Z = zscore(A); Dist = pdist(Z,'seuclidean'); Dist2Matrix = squareform(Dist); Link = linkage(Dist,'ward'); Cluster = cluster(Link,'maxclust',15); C = cophenet(Link,Dist); Err = inconsistent(Link); figure [H,T,perm]=dendrogram(Link,'colorthreshold','default'); set(H,'LineWidth',2) – www.modefinance.com 3/22/2011 14 info@modefinance.com
  • 15. It is possible to define thousands of ratios; in order to avoid redundancy, a first simplification can be done by eliminating highly correlated variables. 50 45 c=corrcoef(database); figure; pcolor (c); figure(gcf) 40 35 30 By their nature, most ratios are 25 correlated each other. The objective 20 should not be selecting completely 15 uncorrelated factors 10 5 5 10 15 20 25 30 35 40 45 50 www.modefinance.com 3/22/2011 15 info@modefinance.com
  • 16. • The selection of the best set of ratios is the first step in the development of a credit scoring model. The set should change according to the sector in which the companies are active. The selection include both statistical approaches and analytical reviews. • Statistical selection tools suggested: – Distribution Analysis; – F-test and t-Student; – Default Frequencies; – CAP plots; – Etc. • We’ll apply these tools in the following slides to 2 ratios: – CAP = (Shareholders Founds)/(Total Assets); – STK = (Stocks)/(Total Assets); www.modefinance.com 3/22/2011 16 info@modefinance.com
  • 17. Simple Statistical Analysis www.modefinance.com 3/22/2011 17 info@modefinance.com
  • 18. • Default Frequency – The x-axis shows the percentile in which a particular ratio value lies and the y- axis shows the default frequency that is observed for firms with ratios in that percentile (Moody’s def). – The relation between a financial statement ratio and default is generally monotonic and “non-linear” CAP STK www.modefinance.com 3/22/2011 18 info@modefinance.com
  • 19. • CAP Plot (Gini Index) – The primary performance measure used by academics was measuring the percentage of misclassifications. This was calculated based on the percentage of defaulting firms that were accepted, and the percentage of non-defaulting firms that were rejected (Type I and Type II errors). Essentially, power curves extend this analysis by plotting the cumulative percentage of defaults excluded at each possible cut-off point for a given model (Source: Moody’s) www.modefinance.com 3/22/2011 19 info@modefinance.com
  • 20. CAP STK www.modefinance.com 3/22/2011 20 info@modefinance.com
  • 21. 1. Z-Score Model: the pioneer predictive tool 1. Dataset selection 2. Ratio definition 3. Credit scoring model selection 4. Discriminant analysis (in sample – out of sample) 2. Credit scoring models 3. Model development: 1. Choosing inputs; 2. Transforming inputs; 3. Combining transformed inputs; 4. PD evaluation 4. Validating techniques 5. Conclusions www.modefinance.com 3/22/2011 21 info@modefinance.com
  • 22. • Transformation of this sort are essential because financial ratios are highly skewed and fat-tailed, which causes a few observations to overly influence the output if not transformed. Transformation methods include: – Replacing the ratio with its percentile; – Turning the ratio into a standard Gaussian variable; – Applying a variety of sigmoidal functions; – Using a nonparametric univariate default estimate generated by each variable Source: Eric Falkenstein studies z = (x-mean(x))./std(x); s = 1 ./ (1 + exp(-z)); plot(x,s,'o') CAP STK www.modefinance.com 3/22/2011 22 info@modefinance.com
  • 23. 1. Z-Score Model: the pioneer predictive tool 1. Dataset selection 2. Ratio definition 3. Credit scoring model selection 4. Discriminant analysis (in sample – out of sample) 2. Credit scoring models 3. Model development: 1. Choosing inputs; 2. Transforming inputs; 3. Combining transformed inputs; 4. PD evaluation 4. Validating techniques 5. Conclusions www.modefinance.com 3/22/2011 23 info@modefinance.com
  • 24. If you follow the previous suggestions (reliable data and info, default info, representative DB, ratio selection, ratio transformation, etc.), doesn’t matter which kind of scoring technique you select. • You can choose among: – Discriminant analysis – Logit and Probit – Kernel density estimators (e.g. SVM) – Neural Networks – Genetic Algorithms – Etc. Maximum Likelihood – Logit function In the training sample T, L is probability (likelihood) of the observed situation (if the π(i) is the probability of observations are independent) observation i being in set B or in set G The problem is that the range of π(i) is [0,1] whereas the predictors can take any real value. Therefore the right- hand side is transformed using a monotonous function. www.modefinance.com 3/22/2011 24 info@modefinance.com
  • 25. 1. Z-Score Model: the pioneer predictive tool 1. Dataset selection 2. Ratio definition 3. Credit scoring model selection 4. Discriminant analysis (in sample – out of sample) 2. Credit scoring models 3. Model development: 1. Choosing inputs; 2. Transforming inputs; 3. Combining transformed inputs; 4. PD evaluation 4. Validating techniques 5. Conclusions www.modefinance.com 3/22/2011 25 info@modefinance.com
  • 26. EBITDA interest coverage ratio ROE Return on equity ROS Return on sales Total Shareholders Founds / Total Assets www.modefinance.com 3/22/2011 26 info@modefinance.com
  • 27. 1. Z-Score Model: the pioneer predictive tool 1. Dataset selection 2. Ratio definition 3. Credit scoring model selection 4. Discriminant analysis (in sample – out of sample) 2. Credit scoring models 3. Model development: 1. Choosing inputs; 2. Transforming inputs; 3. Combining transformed inputs; 4. PD evaluation 4. Validating techniques 5. Conclusions www.modefinance.com 3/22/2011 27 info@modefinance.com
  • 28. www.modefinance.com 3/22/2011 28 info@modefinance.com
  • 29. 1. Z-Score Model: the pioneer predictive tool 1. Dataset selection 2. Ratio definition 3. Credit scoring model selection 4. Discriminant analysis (in sample – out of sample) 2. Credit scoring models 3. Model development: 1. Choosing inputs; 2. Transforming inputs; 3. Combining transformed inputs; 4. PD evaluation 4. Validating techniques 5. Conclusions www.modefinance.com 3/22/2011 29 info@modefinance.com