4.4 Unsupervised Learning
Unsupervised learning finds hidden patterns in data with no labels. Nobody tells it the answers.
Chapter 4: Introduction to Machine Learning (ML)
In unsupervised learning the data has no labels. The model's job is to find structure on its own - like groups of similar things or unusual outliers.
Imagine dumping 10,000 customers into a model with just their shopping habits. It might discover groups like "weekend bargain hunters" and "late-night snack buyers" - categories no one defined in advance. That's called clustering.
It's also great for anomaly detection: spotting the one weird bank transaction that doesn't fit your usual pattern.
Key takeaways
No labels, the model finds structure on its own
Clustering = grouping similar things
Great for spotting anomalies