Contents
1. Descriptive Analytics (What Happened?)
- Objective: Provides insights into past events by summarizing raw data into actionable information.
- Examples: Reports, dashboards, and data visualization that explain key metrics like sales figures, production rates, or customer behavior.
2. Diagnostic Analytics (Why Did It Happen?)
- Objective: Examines historical data to determine the causes behind certain events or trends.
- Examples: Root cause analysis and correlation analysis used to understand why sales dropped or why a machine failed.
3. Predictive Analytics (What Will Happen?)
- Objective: Uses historical data and statistical models to forecast future outcomes or trends.
- Examples: Demand forecasting, risk assessment, and predictive maintenance where AI models predict equipment failures.
4. Prescriptive Analytics (How Can We Make It Happen?)
- Objective: Recommends actions based on predictive insights to achieve desired outcomes.
- Examples: Optimization algorithms, recommendation systems, and automated decision-making in supply chain planning or financial management.
Summary of the Continuum:
- The framework starts from understanding what happened (descriptive), moves to why it happened (diagnostic), progresses to what will happen (predictive), and finally focuses on how to make it happen (prescriptive).
- Advanced analytics blends these approaches with sophisticated algorithms, enabling better decision-making and automation, especially relevant for large-scale IoT data.