Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.datagenie.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
What Dimensional Analysis is

Dimensional Analysis lets you rank any dimension’s values by their contribution to a KPI — either the Top N contributors driving the most positive impact, or the Bottom N segments with the lowest or most negative performance. Use it to validate why an autonomous story moved: once you see which segments drive the change, save them as a Filter Preset so future Top Stories runs stay focused.

​
Top N vs Bottom N

Top N

Shows the dimension values with the highest contribution to the KPI. Use this to understand where performance is concentrated and which segments are carrying the most weight.

Bottom N

Shows the dimension values with the lowest performance or contribution. Use this to identify underperforming segments, declining cohorts, or channels that need attention.

​
How to use it

1

Select a KPI

Choose the metric you want to analyze from the KPI selector in Explorer.
2

Choose a dimension

Select the dimension you want to rank — Country, Channel, Device Type, Customer Cohort, etc.
3

Set Top N or Bottom N

Choose whether you want the highest-contributing values (Top N) or the lowest-performing values (Bottom N). Set the number of results.
4

Interpret the ranking

Review the ranked list. Use this to identify concentration risk or performance gaps.
Use Top N to build your Filter Presets — if the top 3 countries consistently account for the majority of KPI movement, create a preset that isolates them. This makes your Top Stories feed more focused and actionable.

​
What to do next

Correlation Matrix

Understand which KPIs tend to move together before comparing dimensional slices.

Data Playground

Build custom views and freeform comparisons beyond the Top N/Bottom N structure.

KPI Attribution

See how dimensional contribution is used in story generation.