The Process of Data Analysis#

Stage 1 · 📋 Foundations · Lesson 02 of 56 · beginner

◀ Previous · Why Do We Analyze Data? · Next · CRISP-DM for Data Science ▶ · ↑ Section

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

It starts with a question#

Data analysis is a process, not a single act — and it always begins with a question, not with the data. A clear question (“which customers are about to leave?”) decides what data you need, which method fits, and how you will know the answer is good. Skip it, and you risk an elegant analysis of the wrong thing.

The steps#

The workflow moves through recognisable stages:

frame the question and its success criterion;
collect the relevant data;
clean and prepare it into a usable form;
explore it to build intuition and spot problems;
model or analyse to answer the question;
evaluate whether the answer actually holds;
communicate or deploy the result so it drives a decision.

This course walks these stages roughly in order — foundations and understanding first, preparation and modelling in the middle, evaluation at the end.

It loops#

The stages are not a one-way street. Exploring the data often sends you back to collect more; modelling reveals a preparation step you missed; a failed evaluation returns you to the drawing board. Good analysis iterates — circling back as each stage teaches you something the last one could not. The next lesson gives this loop a formal name and shape: CRISP-DM.

Hint