Artificial Intelligence, Data Analytics and Cyber Security - Laws and Practice · Data Analytics

Types of Data Analytics: Descriptive, Diagnostic, Predictive, Prescriptive

Updated 11 October 2026 · Fact-checked

Data analytics is commonly grouped into four types. Descriptive analytics shows what happened. Diagnostic analytics explains why it happened. Predictive analytics estimates what is likely to happen. Prescriptive analytics recommends what to do. In an exam, define each type, give a corporate example, and show how the types build on one another.

Understand Types of Data Analytics

Data analytics means examining data to find patterns and support decisions. The four types answer four different questions, and each one goes a step deeper than the one before.

Descriptive analytics summarises past data. It answers "what happened?" Monthly sales reports, dashboards, board MIS packs and counts of compliance filings made on time are all descriptive. It uses totals, averages, percentages and charts.

Diagnostic analytics looks for causes. It answers "why did it happen?" If sales of a company fell 12% in one region, you drill down by product, price, channel and period to find the reason. Common methods are drill-down, comparison, correlation and root-cause analysis.

Predictive analytics uses past data and statistical or machine learning models to estimate future outcomes. It answers "what is likely to happen?" Examples are forecasting demand, scoring the chance that a borrower defaults, or flagging transactions likely to be fraud. Its output is a probability or forecast, not a certainty.

Prescriptive analytics recommends an action. It answers "what should we do?" It combines predictions with rules, optimisation and simulation. Examples are choosing the best stock level for each warehouse, or suggesting which overdue accounts to chase first. It is usually the most advanced type and needs the most data and computing effort.

The types are not rivals. A company often uses all four together. Value and difficulty generally rise as you move from descriptive to prescriptive.

Key rules to remember

Descriptive analytics: Question: What happened?; Summarises historical data using reports, dashboards and statistics. Hindsight.
Diagnostic analytics: Question: Why did it happen?; Finds causes through drill-down, correlation and root-cause analysis. Understanding.
Predictive analytics: Question: What is likely to happen?; Uses statistical and machine learning models. Output is a forecast or probability. Foresight.
Prescriptive analytics: Question: What should we do?; Recommends actions using optimisation, simulation and rules, usually building on predictions. Action.

How to solve Types of Data Analytics questions

Use this method for any question on types of data analytics, whether it asks you to describe, distinguish or apply them.

1Read the question and note whether it asks for all four types, a comparison of two, or a scenario to classify.
2Define each type needed in one line, anchored to its key question: what happened, why, what next, what to do.
3Give one corporate or governance example for each type, preferably from a company, bank, or compliance setting.
4State the method or output of each type, such as dashboards, drill-down, forecast models or optimisation.
5If the question is a scenario, match each fact in it to the question it answers, then name the type.
6Show the link between types: each builds on the earlier one, and prescriptive often uses predictive output.
7Close with a one-line conclusion, such as which type fits the company's need and one limitation.

Quickest way: Four questions shortcut

When to use it: Use when time is short or you must classify a scenario fast.

Write the four questions in order: What happened? Why? What next? What to do?
Match the scenario to the question it answers.
Past summary means descriptive. Cause means diagnostic. Forecast means predictive. Recommended action means prescriptive.
Add one example per type and one line on how they connect.

Common mistakes in Types of Data Analytics

Calling a sales report that shows last quarter's figures predictive analytics.
Students see numbers and a trend chart and assume it forecasts.
Fix: Ask whether it looks backward or forward. A summary of past data is descriptive.
Treating diagnostic and descriptive analytics as the same.
Both use historical data.
Fix: Descriptive states what happened. Diagnostic explains why, by drilling into causes.
Saying predictive analytics gives certain outcomes.
The word predict sounds exact.
Fix: Write that it gives probabilities or estimates based on past patterns, which can be wrong.
Confusing predictive with prescriptive analytics.
Both look ahead.
Fix: Predictive says what is likely. Prescriptive says what action to take. Prescriptive recommends, predictive forecasts.
Giving definitions without examples.
Students memorise one-liners.
Fix: Add a practical example for each type. Case-based answers earn marks for application.

Worked examples

Example 1

A listed company's compliance team does the following: (a) prepares a monthly report showing the number of board filings made on time; (b) investigates why filings were late in one quarter and finds a delay in obtaining director signatures; (c) builds a model estimating which filings are likely to be late next quarter; (d) uses the model to suggest earlier reminder schedules for specific officers. Identify the type of analytics in each case.

Show the solution

(a) The report summarises past filings. It answers what happened. This is descriptive analytics.
(b) The team looks for the cause of the delays. It answers why it happened. This is diagnostic analytics.
(c) The model estimates future late filings. It answers what is likely to happen. This is predictive analytics.
(d) The reminders are a recommended action based on the prediction. It answers what to do. This is prescriptive analytics.

Answer: (a) Descriptive, (b) Diagnostic, (c) Predictive, (d) Prescriptive.

Example 2

Distinguish between predictive and prescriptive analytics with examples.

Show the solution

Predictive analytics uses historical data and models to estimate future outcomes. Its output is a forecast or probability.
Example: a bank scores each loan applicant on the likelihood of default.
Prescriptive analytics goes further and recommends the best action, using optimisation, simulation or rules, often built on predictions.
Example: the bank uses the scores to recommend approval, rejection or a revised credit limit for each applicant.
Difference: predictive answers what is likely to happen; prescriptive answers what should be done. Predictive informs a decision, prescriptive suggests it.
Both depend on data quality, and neither removes the need for human judgement.

Answer: Predictive analytics forecasts likely outcomes, for example a loan default score. Prescriptive analytics recommends actions based on such forecasts, for example whether to approve a loan or change its limit.

Exam tips

Always lead with the four questions. They give you a clean structure for any answer.
Use a single running example, such as a retailer or a bank, to show all four types and their link.
For scenario questions, quote the words in the facts that signal the type, such as summarised, why, forecast or recommend.
Mention a limitation or ethical point, such as data quality or bias, to show depth in a case-based answer.

Practice questions from Data Analytics

Types of Data Analytics in other exams

The same ground in other exams, if you are preparing for more than one or want another angle on it.

Types of Data Analytics: frequently asked questions

What are the four types of data analytics?

They are descriptive, diagnostic, predictive and prescriptive analytics. They answer what happened, why it happened, what is likely to happen and what to do. Each builds on the previous one.

What is the difference between predictive and prescriptive analytics?

Predictive analytics forecasts likely outcomes using models and past data. Prescriptive analytics recommends the action to take, often using those forecasts with optimisation or simulation.

Which type of analytics is the most advanced?

Prescriptive analytics is generally seen as the most advanced because it recommends actions. It usually needs more data, models and computing effort than the other types.

Do I need examples in the CS Professional exam answer?

Yes. The paper is descriptive and case-based, so a short practical example for each type shows you can apply the idea. Keep each example to one or two lines.