Learning Objectives
By the end of this lesson, learners should be able to:
- Calculate conditional probabilities.
- Interpret conditional probability in business contexts.
- Apply Bayes’ reasoning to update probabilities using new information.
Meaning Of Conditional Probability
Conditional probability measures the probability of an event given that another event has already occurred.
Formula
P(A|B) = P(A and B) ÷ P(B)
Business Example
A retailer finds:
- 30% of customers buy online,
- 12% buy online and use a loyalty card.
P(Loyalty | Online) = 0.12 ÷ 0.30 = 0.40
Interpretation: 40% of online customers use a loyalty card.
Why Conditional Probability Matters
Businesses often receive new information and must update their expectations.
Examples:
- Credit score after loan application,
- Medical test result,
- Fraud alert,
- Customer website behavior,
- Supplier quality inspection result.
Bayes’ Reasoning
Bayes’ reasoning updates probabilities when new evidence becomes available.
Fraud Example
- Probability a transaction is fraudulent = 1%
- Fraud detection system correctly flags fraud = 90%
- System incorrectly flags legitimate transactions = 5%
If a transaction is flagged, the probability it is actually fraudulent is much lower than 90% because fraud is rare. Bayes’ reasoning combines both the fraud rate and test accuracy.
This principle is critical in fraud detection, medical testing, and credit risk analysis.
International Banking Case
A global bank uses machine-learning fraud alerts. Analysts apply Bayes’ reasoning to prioritize investigations and reduce unnecessary customer contact.
Learning Materials / Reference Materials
- Ross, S. A First Course in Probability.
- Khan Academy Conditional Probability and Bayes’ Theorem.
Lesson Summary
Conditional probability measures likelihood under additional information, while Bayes’ reasoning updates beliefs when new evidence becomes available.