Analytics
See what your data is telling you.
Analytics is a sequence of steps, each depending on the one before. Skipping steps is the most common reason analytics fails to change anything.
- Collect
- Prepare
- Analyze
- Visualize
- Predict
- Decide
01
Descriptive analytics
What happened?
Summaries of historical data — totals, rates, distributions, and trends. The foundation of all reporting and the first step in any analysis.
- Region A64
- Region B48
- Region C37
- Region D29
02
Diagnostic analytics
Why did it happen?
Decomposition, segmentation, and correlation analysis to explain movements. Diagnostic work separates real drivers from coincidence.
03
Predictive analytics
What is likely to happen?
Statistical and machine-learning models that estimate future values, always reported with a measure of uncertainty.
04
Prescriptive analytics
What should we do?
Optimization and scenario modeling that compare options under constraints, making trade-offs explicit before a decision is taken.
| Scenario | Cost | Service level |
|---|---|---|
| Option A | 100 | 92% |
| Option B — recommended | 112 | 97% |
| Option C | 94 | 86% |
05
Real-time analytics
What is happening now?
Streaming data processed as it arrives, used for monitoring and alerting where delay has a cost.
Stream 1
Stream 2
Stream 3
Stream 4
Have a data problem worth solving?
Tell us what you are trying to understand or decide. We will reply with an honest view of how analytics could help.