A type of artificial intelligence where systems learn patterns from data and improve their performance through experience, rather than following explicitly programmed rules.
In traditional programming, a developer writes rules that tell a computer what to do. In machine learning, a developer provides data and a learning algorithm, and the system discovers the rules itself. The resulting model can then make predictions or decisions on new data it has not seen before.
Common machine learning tasks include classification (is this email spam?), regression (what will this property sell for?), clustering (which customers have similar behaviour?), and recommendation (what should this user see next?).
Example: A provincial government trains a machine learning model on historical property assessment data to predict assessed values for new properties. The model learns the relationship between property attributes (size, location, age, type) and assessed value from thousands of historical examples, then applies that learned relationship to estimate values for properties not yet assessed.
Machine learning models can perpetuate or amplify biases present in training data. Responsible use requires careful attention to data quality, fairness, and transparency.