CurriculumGrades 9-12Computer Science

Data science, modeling, and machine learning basics

Aligned to CSTA-DA — CSTA K-12 Computer Science Standards.

What this lesson teaches

Data science means working with real datasets to find patterns and build computational models that make predictions. Machine learning systems are trained on examples rather than directly programmed, so the data you feed them shapes what they learn. That is powerful, but it also means a model trained on biased or incomplete data will make biased or wrong predictions, which is why understanding its limits matters as much as its power.

Worked example

A streaming app recommends shows by learning from what you and others watched. If it was only ever trained on action movies, it would keep suggesting action movies and struggle to recommend a documentary you might love, because its training data was incomplete.

Practice questions

  1. How is machine learning different from writing step-by-step instructions yourself?
  2. Why can a model trained on biased data produce biased results?
  3. Give one example of a prediction system you use and one situation where it might fail.

Watch the lesson

Every lesson comes with a video taught in English and Spanish — the same video the QR code in the printed workbook opens.

▶ Watch this lesson

En español

Ciencia de datos, modelos y conceptos básicos de aprendizaje automático

La ciencia de datos consiste en trabajar con conjuntos de datos reales para encontrar patrones y construir modelos computacionales que hagan predicciones. Los sistemas de aprendizaje automático se entrenan con ejemplos en lugar de ser programados directamente, así que los datos que les das determinan lo que aprenden. Eso es muy poderoso, pero también significa que un modelo entrenado con datos sesgados o incompletos hará predicciones sesgadas o incorrectas, por eso entender sus límites es tan importante como conocer su potencial.

Ejemplo: Una aplicación de streaming recomienda series aprendiendo de lo que tú y otros usuarios han visto. Si solo fue entrenada con películas de acción, seguirá sugiriendo películas de acción y le costará recomendarte un documental que podrías amar, porque sus datos de entrenamiento fueron incompletos.

Teach this lesson today

An AI tutor that guides with questions instead of just giving answers — all K–12 core subjects, every child in the family.

Start free — no card required