• Introduction
  • Data Science
Theoretical Background for Credit Risk
  • What is Credit Risk
  • Expected Losses
Data Overview
  • Data Overview
  • What type of Data do we have
Preprocessing Data
  • Combining Data
  • How do we combine data when we have labels instead of Numbers
  • Creating Gender Dummy Variables
  • How Many Genders do we have in our Data
  • Creating Ownership Dummy Variables
  • What function do we use when we create dummy variables
  • Relationship Status Dummy Variables
  • Coding of the Dependent Variable
  • Weight of Evidence Male and Female
  • Weight of Evidence - Rural vs Urban
  • Weight of Evidence- School Level
  • Weight of Evidence- Work Sector and Residence
  • Weight of Evidence - Relationship Status
Continuous Variables
  • Continuous Varisbes
  • .Coding of Variables Age in Years
  • Coding of variables: Maturity of the Loan
  • Multicollinearity of Variables
  • Weight of Evidence for Age in Years
  • Weight of Evidence Maturity
Choosing Variables for Machine Learning Algorithm
  • Choosing Variables for Machine Learning Algorithm
  • Installing Real Statistics
Running the Machine Learning Algorithm
  • The meaning of Results
Validation of Results
  • Applying the results into test dataset