Introduction to Machine Learning Approaches (HL)
This subtopic explores three powerful machine learning approaches used in real-world systems:
- Linear Regression , predicting continuous numerical outcomes
- Association Rule Learning , discovering patterns and relationships in large datasets
- Reinforcement Learning , training agents to make decisions through interaction with an environment
Each approach suits different types of problems, and understanding when and how to apply them is a key skill for IB Computer Science HL.
All three approaches covered here are HL only. You are expected to understand the underlying concepts, key metrics, algorithms, and real-world applications of each.
Linear Regression: Core Concepts
Linear Regression: A statistical method used to model the relationship between a dependent variable (the response variable) and one or more independent variables (predictor variables), with the goal of finding a linear equation that best predicts outcomes.
The two key variables in any linear regression model are:
- Dependent Variable (): The outcome we want to predict (e.g., house price, salary)
- Independent Variable (): The input used to make predictions (e.g., house size, years of experience)
Think of the independent variable as the cause and the dependent variable as the effect. In predicting house prices, the size of the house (independent variable) influences the price (dependent variable) , not the other way around.
Linear regression assumes a linear relationship between variables , meaning the change in is proportional to the change in . This makes the model interpretable and computationally efficient, but limits it to problems where this assumption holds reasonably well.