Business Analytics Course [2026] | Master Business Strategy & Data-Driven Decisions

Lesson 1.4 – Types of Business Analytics

📖 Lesson 1.4 — Types of Analytics

Understand the four core categories of analytics — Descriptive, Diagnostic, Predictive, and Prescriptive — and how each answers a different business question.

Analytics is often categorized into four types. Each type builds on the previous one — starting from describing events to prescribing actions. Businesses use these layers to move from reporting to forecasting to automation of decisions.

Descriptive

What happened?

Diagnostic

Why did it happen?

Predictive

What will happen?

Prescriptive

What should we do?

📊 Descriptive Analytics — What happened?

Descriptive analytics summarizes historical data to show trends, patterns, and performance. Reports, dashboards, and summary statistics are classic descriptive outputs. This is the foundation — without a clear picture of the past, you can’t explain or predict the future.

Common outputs: monthly sales report, KPI dashboards, conversion rates, churn rates.
Techniques used: aggregation, visualization, summary statistics, pivot tables.

Example

An e-commerce manager reviews last month’s sales dashboard to see top-selling categories and regions. The dashboard shows a 18% drop in category X and a 12% uplift in region Y.

Action Tip: Build a single-page dashboard with your top 6 KPIs to review weekly.

🔎 Diagnostic Analytics — Why did it happen?

Diagnostic analytics digs into the reasons behind outcomes. Analysts use drill-downs, segmentation, correlation, and root-cause analysis to uncover drivers that led to the observed results.

Common outputs: root-cause reports, cohort analysis, funnel diagnostics.
Techniques used: correlation analysis, hypothesis testing, cohort & funnel analysis, regression for explanation.

Example

Conversion fell 10% last month. Diagnostic work shows the drop is concentrated in mobile users after checkout page load times increased. The root cause: recent site update increased load time on specific devices.

Action Tip: Segment traffic by device and conduct an A/B rollback test to confirm the hypothesis.

🔮 Predictive Analytics — What will happen?

Predictive analytics uses historical patterns to forecast future outcomes. Techniques such as time-series forecasting, regression models, and classification algorithms help estimate sales, churn, demand, and more. Predictive models assign probabilities to future events — enabling proactive planning.

Common outputs: sales forecasts, churn probability scores, demand predictions.
Techniques used: time-series models, regression, classification, survival analysis.

Example

A retail chain uses seasonal demand forecasts to stock warehouses — predicted demand indicates higher need for winter products in northern regions. Forecasting reduces stockouts and discounting.

Action Tip: Start with a simple 3-month moving-average forecast and compare it to actuals; refine using seasonal decomposition.

🧭 Prescriptive Analytics — What should we do?

Prescriptive analytics goes beyond predicting outcomes to recommending actions and optimizing decisions. It uses optimization, simulation, and business rules to suggest the best course of action under constraints.

Common outputs: price recommendations, inventory reorder points, marketing offers tailored by customer segment.
Techniques used: optimization (linear/non-linear), constraint programming, simulation, decision rules.

Example

An airline uses prescriptive models to allocate seats for overbooking: models calculate optimal overbook numbers to maximize revenue while minimizing denied boarding risk.

Action Tip: Convert forecasts into decision rules (e.g., reorder if predicted stock < threshold) and monitor outcomes.

🔗 How the Types Work Together

Start with descriptive reports to know what happened → use diagnostic analysis to find causes → build predictive models to forecast outcomes → apply prescriptive rules and optimization to automate the best actions. The maturity curve helps organisations move from reporting to intelligent automation.

📌 Key Takeaways

Descriptive: Summarize the past. Dashboards & reports.
Diagnostic: Explain the reasons. Root-cause & segmentation.
Predictive: Forecast the future. Probabilities & scores.
Prescriptive: Recommend actions. Optimization & decision rules.

Mini Challenge

Identify one KPI (descriptive).
List 2 possible causes for a change (diagnostic).
Suggest a 1-month forecast target (predictive).
Write one rule you would take if forecast < target (prescriptive).

➜ Continue to Lesson 1.5 – Analytics Lifecycle