Supervised Learning

Full definition

Tasks split into classification (discrete labels — spam/not-spam, fraud/legit) and regression (continuous values — price, demand). Supervised learning is "supervised" because a human or system has supplied the correct answer for every training example. Quality and quantity of labels typically determine final model accuracy more than the choice of learning algorithm.

Why it matters

Most enterprise AI value today — fraud detection, demand forecasting, medical imaging triage, churn prediction — is supervised learning. The hard, expensive part is producing high-quality labeled data; the modeling itself is increasingly commoditized.

Example

An insurer trains a model on 10 million historical claims, each labeled "fraudulent" or "legitimate," then deploys it to score new claims at intake.

Related terms

• Machine Learning (ML)
  Machine Learning (ML) is the subfield of AI in which algorithms improve their performance on a task by learning statistical patterns from data, rather than following rules a human wrote by hand.
• Training Data
  Training data is the curated dataset used to teach a machine-learning model — every pattern the model can recognize, every bias it inherits, and every limit to its accuracy ultimately traces back to this data.
• Unsupervised Learning
  Unsupervised learning is a machine-learning paradigm where a model is given only inputs — no labels — and must discover structure in the data: clusters, density, low-dimensional representations, or anomalies.
• Fine-tuning
  Fine-tuning is the process of further training a pretrained model on a smaller, task-specific dataset so it specializes in a particular style, domain, or behavior — without retraining from scratch.
• Model
  An AI model is the trained artifact — a specific set of numerical weights plus an architecture — produced when a learning algorithm runs against training data, and the thing that actually gets deployed and audited.