ClientA global crop nutrition company
SprintAn 8 week sprint
Fieldwork175,386 orders analysed across 4 seasons
Customer Experience
Loyalty was not where they thought
The client wanted to know how its farmer customers actually buy, from four years of its own order data rather than from opinion. The data existed. It was not usable.
175,386
Orders analysed, after 25,345 rows were removed as unusable
24,499
Customers segmented by loyalty across five regions and four seasons
11 points
Spread in loyal customer share between the most and least loyal region
A note on sourcing. Every figure here comes from a SprintlyWorks client engagement. Clients are described, never named. Where a figure is identified, modelled or indicative rather than banked, the line says so.
01
The problem
The order history was there, and it could not answer the question. Rows carried missing or junk addresses. Deliveries were recorded with zero volume. There was no segmentation, so nothing separated a farmer who buys every season from one who bought once and never returned.
The first four weeks of the sprint went on building the dataset rather than reading it. Two hundred thousand rows came down to 175,386 through four cleaning passes, each of which had to be decided on and documented rather than guessed at.
02
What the sprint set out to do
Analyse four years of buying behaviour by geography, by distributor, by product line and by point in the season. Establish who stays loyal, who skips a season and returns, and which distributors hold which customers. Then hand over a reusable analysis tool and a manual so the client could keep asking the question without asking again.
The answer that mattered was not the headline loyalty rate. It was that loyalty is not uniform: the strongest region runs eleven points ahead of the weakest, and a third of the most loyal farmers buy through more than one distributor.
Five regions, four seasons
Loyalty is a regional fact, not a national one
Customers by how many seasons they ordered in, per region.
| Region | Customers | Ordered every season | Skipped three |
|---|---|---|---|
| All regions | 24,499 | 43.6% | 22.4% |
| Region 1 | 7,275 | 49.2% | 19.7% |
| Region 2 | 3,954 | 42.5% | 24.0% |
| Region 3 | 4,922 | 38.1% | 25.0% |
| Region 4 | 5,070 | 42.0% | 23.7% |
| Region 5 | 3,365 | 42.3% | 21.4% |
How to read this → A single national loyalty figure of 43.6% hides an eleven point spread underneath it. Region 3 loses a quarter of its customers for three seasons out of four while Region 1 keeps almost half of them buying every season. Those are two different commercial problems and they were being managed as one.
SprintlyWorks analysis
Download the full case study
Have a similar requirement?
Contact us today to learn more about on-demand workforce and accelerate development on your most pivotal projects!
Quick Reads for Big Impact
Featured Case Studies
Quick Reads for Big Impact
Accelerating Success for Enterprises in 20+ Geographies
Launch Your Sprint with
Define your project, connect with top-tier consultants, and start making progress fast.