5/16/24Less than 1 minute
- Descriptive Analytics – What has happened?
- Predictive Analytics – What might happen?
- Prescriptive Analytics – What should we do? What is the best course of action for a given situation?
Prescriptive Analytics
- Self-driving cars
- Automatically adjusting airline ticket prices based on customer demand, weather and oil prices
- What TV show will be popular?
- Diagnosis and treatment suggestions in health care
- Decision on mortgage, loan, credit card application
To be able to make a decision, to compare possible actions, we need to quantify the effect of future decisions…
- Students – grades
- Machine Learning – loss function
- Clustering – distance
- Finance – return and risk
- Banking – credit scoring
Identify (prescribe) a number of different possible actions
Quantify the effect of future decisions in order to advise on possible outcomes before the decisions are actually made
Use business rules, algorithms, machine learning and computational modelling procedures
A right to explanation is a legal right to be given an explanation for an output of the algorithm
Credit Scoring and Credit Scorecards
- Credit scoring is defined as a statistical model that assigns a risk value to prospective or existing credit accounts.
- A credit scorecard is a statistical risk model that was put into a special format designed for ease of interpretation.
- After the credit scorecard model is built, it is used to make strategic decisions such as accepting/rejecting applicants and deciding when to raise a credit line, as well as other decisions.
[page 8]