Customer model
One grain for customer, order and subscription analysis, with the rules written down.
Ecommerce and D2C
One customer view across channels
Ecommerce stacks grow quickly. Storefront, payments, subscriptions, email and ad platforms all describe the same customer in different ways. We build the model that lets those numbers be compared.
Common sources
- Commerce
- Shopify · Stripe · Recharge
- Marketing
- Klaviyo · Meta Ads · Google Ads
- Data layer
- Snowflake · dbt · Tableau
The problem
What ecommerce teams usually notice first
The store, finance report and marketing platform can all be right in their own terms. That does not mean they can answer the same question.
Customers are counted more than once
Guest checkout, subscription accounts and email profiles often create several records for one buyer.
Channel spend is hard to compare
Each platform claims credit in its own way, so marketing decisions are made from numbers that do not share a base.
Retention depends on manual exports
Cohorts, repeat purchase and subscription health often live in ad hoc spreadsheets that are hard to repeat.
The approach
Build the customer grain first
We start by agreeing what a customer, order, subscription and return mean for your business. The reporting then reads from that shared model instead of from whichever platform was easiest to export.
Customer identity rules
The model says how records are joined, where the limits are, and which source wins when systems disagree.
Cohorts and retention
Repeat purchase, churn, subscription health and product behaviour can be measured on the same base.
Spend and revenue in one view
Paid, email and onsite activity are compared against agreed revenue and margin measures, not each platform's own answer.
What the work can include
Start with one reporting pain, then build only the data layer needed to make it reliable.
Marketing performance
Spend, revenue and attribution inputs brought together so channel choices use the same definitions.
Trading dashboard
A small set of trading measures that explains what changed and where to look next.
What clients say
Igor worked with us at Manual as an independent Tableau contractor. He clearly knows Tableau inside out and built us some great dashboards.
He was pragmatic, understood the balance of £ vs speed, and was willing to adapt his designs and approach appropriately. He was able to work independently and great at managing his own workload - a pleasure to work with.
Mark Madge
Head of Data, Manual
Before I worked with Igor, I said dashboard was “the D word.” He often anticipates what I would need.
I review and think “but what about… “ and he’s already thought of it. I focus on giving him the priorities; the questions we need to answer; and for what audience.
And he delivers every time. I feel overall more capable and effective due to Igor’s work.
He’s a joy to work with. I’m very happy to recommend him.
Heather McNamee
Service Manager, Techoir
It was my huge pleasure to work with Igor on a data project where he was delivering different dashboards over a few weeks remotely. The scope of the work was constantly changing but thanks to Igor's professional approach he mastered it perfectly.
His strength: organized, clear, on top of things, communicates well, proactive and involves stakeholders when necessary. Its a great feeling to know that your projects are in good hands - in those of Igor.
Zdenka de Booij
Account Executive, InterWorks
How an engagement usually starts
Choose the decision
We name the decision the reporting must support, such as stock, spend, retention or trading performance.
Agree the customer rules
Identity, order, refund and subscription definitions are written before the dashboard is designed.
Model the sources
Commerce, marketing and finance data are joined in the warehouse with tests around the key assumptions.
Hand over the repeat path
Your team gets the docs and checks needed to update the work as the channel mix changes.
Questions commerce teams ask early
Do we need perfect identity matching?
No. We need useful, stated rules and a clear view of what they can and cannot answer.
Can you work around platform attribution?
Yes. Platform attribution still has a role, but it should not be the only way the business judges spend.
Can this start with one channel or product line?
Yes. A narrow start is often better, because it proves the rules before the model grows.
Next step
Which number do you not trust?
Bring the report nobody trusts. We will tell you what is actually wrong underneath it.
Thirty minutes, straight to the problem. No deck, no pitch, and a written summary afterwards either way.