Support Is Not Lift
Hard About 40 min Katabench Pro
Extend basket affinity with marginal counts, confidence in both directions, and lift.
The full brief is part of Katabench Pro
Pro opens this kata's brief, its starter code and its grader. To see how the track works first, try Customer Order Totals, which is free.
How it is graded
Your LINQ or SQL runs against real PostgreSQL. You see the SQL your code generates on the sample tests and can inspect its execution plan, so you learn when the database did the wrong work.
What it practices
- Aggregation grain
- Aggregate each fact at its own grain so joins do not multiply totals.
- Statistical aggregates
- Medians, percentiles, distributions, weighted averages and regression computed in SQL.
Do these first
Related katas
- How Concentrated Is Each Market? Hard Pro Compose customer and country aggregates to calculate a revenue concentration index.
- Acquired, Then Returned Hard Pro Build a first-purchase cohort and preserve countries whose acquired customers never returned.
- Similar Buyers, Not Just Heavy Buyers Hard Pro Rank customer purchase sets by intersection-over-union similarity, so a large overlapping catalog does not automatically beat a close match.
- The Same Basket in Different Lines Hard Pro Compare order baskets as product-to-total-quantity multisets, independent of line splitting, prices, totals, and row order.