Browse Microsoft Certification Guides

Azure AI-900 ML Model Types Guide

Study Azure AI-900 ML Model Types: key concepts, common traps, and exam decision cues.

AI-900 uses machine-learning questions to test whether you understand the shape of the answer, not whether you know algorithm internals. Start with the output type. If the output is a number, category, or unlabeled grouping, the technique usually follows directly.

Supervised learning: Learning from labeled examples where the correct answer is already known during training.

Choose the technique by output

Technique Use it when… Typical business example
regression the output is a number forecast sales, price, or wait time
classification the output is a category or label fraud or not fraud, approve or deny, churn or stay
clustering the goal is unlabeled grouping customer segmentation or grouping similar incidents

Supervised vs unsupervised

Question Strongest answer
Do labeled target outcomes exist? supervised learning is possible
Do you only want to discover patterns or groups? unsupervised learning is the stronger first fit

Classification and regression are supervised because they depend on labels. Clustering is unsupervised because it groups data without predefined labels.

Where deep learning and transformers fit

Term AI-900 takeaway
deep learning neural-network-based approach used for complex patterns, especially in images, audio, and language
transformer architecture model architecture heavily used in modern language and generative-AI systems

AI-900 does not expect low-level model math. It expects you to know that deep learning is useful for complex pattern recognition and that transformers are foundational in modern language and generative systems.

Common traps

Trap Better reading
choosing classification when the output is a number use regression for numeric prediction
choosing clustering when labels already exist clustering is for unlabeled grouping
assuming all advanced ML is generative AI deep learning can power many predictive and perception tasks too

What strong answers usually do

  • classify the output type first
  • ask whether labels already exist
  • separate grouping from prediction
  • recognize deep learning and transformers as model-family ideas, not as replacements for basic task classification

Decision order that usually wins

  1. First ask whether the output is a number, a label, or an unlabeled grouping.
  2. If the output is a numeric value, think regression.
  3. If the output is a category or class, think classification.
  4. If the task is grouping similar items without known labels, think clustering.
  5. AI-900 usually rewards identifying the target-output shape before anything more technical.

Quiz

Loading quiz…
Revised on Sunday, May 10, 2026