Stages of Analytics

Analytics is commonly broken down into four progressive stages. Each stage answers a deeper question than the one before it, and together they form a natural maturity path for how organisations use data.

1. Descriptive Analytics - "What happened?"

Summarises historical data using reports, dashboards, and basic statistics. Example: "Total sales last quarter were 12% higher than the quarter before."

2. Diagnostic Analytics - "Why did it happen?"

Digs deeper into the descriptive findings to identify causes, often using techniques like drill-downs and correlation analysis. Example: "Sales rose because of a festive-season discount campaign."

3. Predictive Analytics - "What is likely to happen?"

Uses statistical models and machine learning on historical data to forecast future outcomes. Example: "Based on past trends, sales are expected to rise by 8% next quarter."

4. Prescriptive Analytics - "What should we do about it?"

Goes a step further to recommend specific actions, often using optimisation techniques. Example: "Increase inventory for the top 3 selling products by 15% ahead of the festive season."

Most organisations start with descriptive analytics because it's the easiest to implement, and gradually move toward predictive and prescriptive analytics as their data maturity grows.

Coming Up Next

Next, you'll look at a widely used framework for running a Data Science project end to end - the CRISP-DM life cycle.

Ready to Master Data Science?

Join Uncodemy's Data Science Course and build real, job-ready skills with expert mentors.

Explore Course