Stop guessing why the number moved
Decompose changes in any KPI into the underlying drivers, ranked by contribution, automatically.
faster than manual variance analysis at typical pilot customers
What's broken today
Variance reports tell you the number changed, not why.
Manual decomposition takes a week and an analyst.
Leadership wants the explanation in the meeting, not a follow-up email.
Built for the way operators actually work
Automatic variance decomposition
Pick a KPI and a comparison period. We'll rank what drove the change.
Driver importance with statistical rigor
Shapley-style attribution, not just correlation. We show contribution and confidence.
Plain-English explanations
Every driver comes with a one-sentence explanation a non-analyst can use in the meeting.
Ask PredictWave anything
Three steps to your first prediction
Pick the metric you care about
Revenue, churn, margin, conversion. Anything in your warehouse.
Choose what to compare
Quarter-over-quarter, vs. plan, vs. forecast, vs. last year.
Read the answer
Ranked drivers, contribution percentages, and a short narrative summary.
What you'll need
These are the typical data sources for key drivers analysis. You don't need every source on day one. Start with what you have.
- The metrics already in your warehouse
- Dimension tables (region, product, segment)
- No new data required
Try Key Drivers Analysis on your own data
Free for 14 days. No credit card. No data scientist required.