Development of scoring models bases on methods well known from other applications. It makes use of specialized methods that are dedicated to building scoring models. You will learn about methods from these two groups. A strong basis for further learning will be understanding of multistage scoring model development process.

After this training you will be able to build a scoring model. It may be your first model. It will happen even if you will start the training without any knowledge in developments of scoring models.

The training bases on R. Thanks to this fact you will be able to work on your own data using this tool. As your experience will grow you will prepare your own set of methods and R functions for building models. It will suit you: effective, convenient, and using powerful methods — methods you like to use and appropriate for specificity of credit portfolios and data you work with.


What will you learn?

  • You will be able to build a scoring model. Even if you will start without any knowledge in this topic.
  • Learn all the stages of the scoring system development process: starting from gathering data, through selection of best features, determination of scoring points, quality assessments, up to monitoring of a working system.
  • Learn how to preprocess data for development of scoring systems.
  • What are statistical methods that are applied there.
  • Learn how to solve problem of lack of information about rejected applications (reject inference).
  • Get knowledge and skills in assessment of quality of scoring models.
  • Learn essential basics of R.
  • Work on these topics hands-on with a computer: we use R and RCommander.
  • You will get comprehensive materials and R scripts allowing you working single-handedly on your data.


For whom is this training?

Employees of credit risk, CRM, audit, and IT departments who:

  • build scoring models or willing to start building them,
  • monitor working scoring models,
  • validate existing models,
  • are credit risks analysts,
  • are for any reason interested in learning how to build a scoring system and how it works.

Even if you don’t use R you will benefit from the training. The methods introduced are best practices and are accessible in many statistical tools. R aims as a illustrative facility. Thanks to using R in the training you will get knowledge and practical skills undependent of commercial software.


Shortened agenda

  • Short introduction to R
  • Stages of a complete scorecard development process
  • Analysis and transformation of characteristics used to building scoring system
  • Logistic regression: theory and practice
  • Selection of characteristics for building scoring models
  • Methods of assessing of predictive power of scoring systems
  • Reject inference: taking into account rejected applications
  • Using of scoring systems


Full agenda

  1. Short introduction to R
    • introduction to R environment
      • specificity and survey of capabilities of R
      • installation and configuration
      • using R
      • help system
      • GUI
      • using built-in function
    • basics of R: data types and data structures
      • types of variables
      • objects and their main properties (vectors, matrices, strings, lists and data frames)
      • basic operations on objects
    • elements of programming in R language
      • basics of R language
      • controlling of code flow
      • writing own scripts and functions
  2. Introduction
    • credit risk assessment before credit scoring
    • areas of application of credit scoring
    • idea of working: using of historical data to foresee future behaviour of clients
    • pros and cons of credit scoring
    • advantages of using credit scoring
    • types of credit scorings
      • basing on area of application
      • basing on way of development
      • joining sereval scoring systems
  3. Stages of a complete scorecard development process
    • organization of the project (including definition of a business goal)
    • preliminary data analysis
    • definition of project parameters
      • definition of good and bad client: transformation of business goal into a statistical goal
      • application window and performance window
      • exclusions
      • segmentation
    • data preparation
      • characteristics used in credit scoring
      • selection of a development sample
      • gathering and cleaning data
    • building of a scoring card
      • analysis and transformation of characteristics used to building scoring system
      • logistic regression: theory and practice
      • selection of characteristics for building scoring models
      • methods of assessing of predictive power of scoring systems
      • reject inference
    • using of scoring systems
      • summary of the process: scorecard management reports
      • implementation of a scorecard (including cut-off point selection: iso-risk, iso-acceptance)
      • monitoring
  4. Analysis and transformation of characteristics used to building scoring system
    • analysis of single characteristics
      • Weight of Evidence, odds
      • distributions of characteristics (contingency tables, histograms)
      • handling of missing data and outliers
      • quality control and cleaning of data
      • preliminary choice of characteristics for building a model – analysis of discriminative power of characteristics
    • classing (discretization) for numeric characteristics
      • role of discretization
      • discretization using weight of evidence (WoE)
    • analysis of dependency of characteristics and construction of generated characteristics (cross characteristics)
  5. Logistic regression: theory and practice
    • an introduction to logistic regression
      • advantages of logistic regression
      • regression models – an introduction on example of linear regression
      • what is scoring: linear model, logit and probit models
    • idea of model in three approaches: dummy variables, WoE encoding, continuous variables
    • statistical basics
    • building of model, practical and theoretical properties
    • applied approaches to building scoring systems using logistic regression
    • interpretation of results
    • diagnostics of model: statistical tests and plots
    • statistical inference for logistic regression
    • other methods of building scoring systems and their pros and cons
  6. Selection of characteristics for building scoring models
    • introduction to assessment of predictive power of scoring models
    • criteria of using characteristics in scoring models: statistical, business, operational
    • Information Value of a characteristic
    • complete search
    • other feature selection methods
      • forward and backward feature selection methods basing on classification quality
      • stepwise methods basing on AIC criterion
  7. Methods of assessing of predictive power of scoring systems
    • goodness of fit criteria (AIC, R^2)
    • analysis of predictive power of model
    • distributions of scoring points
    • assessment of classification quality: confusion matrix
    • assessment of discriminative power: ROC curve, AR, KS, and divergence measures
  8. Reject inference: taking into account rejected applications
    • an idea of reject inference
    • overview of reject inference methods
      • define as bad
      • extrapolation
      • augmentation
  9. Using of scoring systems
    • selection of cut-off
    • implementation of scoring systems
    • monitoring of effectiveness of scoring systems and reporting
      • monitoring of predictive power of system
      • monitoring of predictive power of characteristics
      • monitoring of population stability
    • champion-challenger strategies

Try again