Credit Scoring

Credit Scoring

1. The advent of data analytics

   • Data has the potential to transfor business and drive the creation of business value.
   • In the Financial Industry some examples of using data analytics to create business value include fraud detection, customer segmentation, employee or client retention.
   • In order for data analytics to reveal its potential to add value to business, a certain number of ingredients need to be in place.
     • Distributed file systems
     • Database management
     • Advanced analytics

2. Is a tool that is typically used in the decision-making process of accepting or rejecting a loan.

   • Allows one to distinguish between "good" and "bad" loans and give an estimate of the probability of default.
     • A loan implies a certain number of possible applications
       • Health score
       • New clients
       • What drives default

3. A credit scoring model is just one of the factors used in evaluating a credit application. Assessment by a credit expert remains the decisive factor

4. Data quality

   • There is an important step of preprocessing .This provides a first insight into the patterns inside the data.
     • The investigation in this phase includes the following aspects
       • What is the proportion of defaults in the data?
       • What is the frequency of values in each variable in the data?
       • What is the proportion of outliers in the data?
       • How many missing values are there and what is the reason?
       • Quality assurance

5. Model development

   • Default definition: this definition lies un the heart of the model
   • Training versus generalisatio error
   • Reject inference
   • Logistic regresión
   • Clsification: distinguish between good and bad
   • Variable selection
   • Information value

6. Model performance

   • Goodness od Fit
     • Is the data contained one response variable
   • 1.- It fits the existing data
   • 2.- It can produce the correct probability of default on data that it has not seen before
   • Predictive power
     • The most common way is through the computation of the histograms

7. Skantzos, N. & Castelein, N. (2016). Credit scoring Case study in data analytics. Deloitte.

   • Doy mi palabra que he realizado esta actividad con integridad académica