Bases de donnéesConnectez n'importe quelle base de données et analysez vos données instantanément·FichiersImportez des fichiers CSV ou Excel et explorez-les avec l'IA·ChatPosez vos questions en langage naturel — dialoguez avec vos données·Tableaux de bordCréez des dashboards interactifs à partir de vos requêtes en quelques secondes·IALaissez l'IA écrire le SQL à votre place·GraphiquesVisualisez les tendances avec des graphiques générés automatiquement·No-codeAucune connaissance SQL requise — demandez simplement en français·PartagePartagez vos dashboards en direct avec votre équipe en un clic·InsightsDétectez automatiquement les tendances et anomalies cachées dans vos données·ExportsTéléchargez vos résultats en CSV, Excel ou PNG instantanément·Bases de donnéesConnectez n'importe quelle base de données et analysez vos données instantanément·FichiersImportez des fichiers CSV ou Excel et explorez-les avec l'IA·ChatPosez vos questions en langage naturel — dialoguez avec vos données·Tableaux de bordCréez des dashboards interactifs à partir de vos requêtes en quelques secondes·IALaissez l'IA écrire le SQL à votre place·GraphiquesVisualisez les tendances avec des graphiques générés automatiquement·No-codeAucune connaissance SQL requise — demandez simplement en français·PartagePartagez vos dashboards en direct avec votre équipe en un clic·InsightsDétectez automatiquement les tendances et anomalies cachées dans vos données·ExportsTéléchargez vos résultats en CSV, Excel ou PNG instantanément·
AnalityQa
FonctionnalitésPar métierTarifsOutilsBlog
ConnexionCommencer
Blog›E-commerce

Segment Your Customers by Behaviour, Not Just Demographics

Knowing who your customers are is less useful than knowing which ones are about to churn, which are worth a VIP offer, and which have gone silent. AnalityQa AI AI answers those questions from your order history in minutes.

Try AnalityQa AI AI free →See live examples
E-commerce fulfillment boxes

The problem

  • →Most e-commerce teams treat their customer base as a single audience, sending the same campaigns to everyone and missing the revenue that targeted segmentation unlocks.
  • →RFM analysis — recency, frequency, monetary value — is a proven segmentation framework but requires joining order history at the customer level, a query almost no one runs without a data analyst.
  • →High-LTV customers are identified anecdotally rather than systematically, meaning VIP programmes are based on gut feel rather than data.
  • →Dormant customers who last purchased 90 or 180 days ago represent recoverable revenue, but building a reactivation list requires a query against order history that Shopify's built-in tools cannot produce.

Why the usual approach breaks down

Shopify's customer reports do not compute RFM scores

Shopify shows individual customer order counts and lifetime spend, but it does not calculate recency, frequency, or monetary scores or place customers into segments. Getting RFM requires exporting every customer's order history and running a cohort calculation — typically in SQL or Python.

Joining order history to customer records requires SQL

LTV, purchase frequency, and inter-purchase intervals all require aggregating order-level data to the customer level with GROUP BY and window functions. This is a well-understood SQL pattern, but it is beyond what most e-commerce ops or marketing teams can write and maintain.

CRM and Shopify data are siloed, making behavioural personas incomplete

Shopify knows what customers bought. Your email platform knows who opened what. Your ad platform knows who clicked which ad. Combining these signals into behavioural personas requires a join that spans at least two separate data exports — a cross-system merge most teams never attempt.

Cohort LTV calculations drift as your product mix changes

LTV projections built on historical averages become misleading when your product mix, pricing, or customer acquisition channel shifts. Keeping cohort LTV current requires rerunning the calculation regularly — which means it almost never gets done.

How AnalityQa AI AI solves it

Upload your data — or connect it live — and ask in plain English.

01

Upload your Shopify order export and get RFM scores immediately

Drop your Shopify orders CSV into AnalityQa AI AI. The system aggregates order history to the customer level, computes recency, frequency, and monetary scores, and assigns each customer to an RFM segment — no configuration required. You can ask follow-up questions about any segment in plain English.

02

Identify your top LTV cohort and what makes them different

Ask 'Who are my top 10% customers by lifetime value, and what products did they first purchase?' and AnalityQa AI AI returns a table of your highest-value customers alongside their first-purchase product and acquisition channel if available — giving you a clear picture of what a VIP customer looks like.

03

Build a dormant-customer reactivation list in seconds

Type 'Give me all customers who bought at least twice but have not purchased in the last 120 days, sorted by lifetime value' and receive an exportable list you can upload directly to your email platform. No SQL. No manual filtering.

04

Join your email or ad data to enrich segments

Upload a CRM export or email engagement CSV alongside your order data. AnalityQa AI AI joins them on customer email or ID and lets you ask questions like 'Which RFM segment has the lowest email open rate?' — connecting purchase behaviour to channel engagement in a single query.

05

Schedule a customer health dashboard for your team

Pin your RFM distribution chart, VIP list, and dormant-customer count to a shared dashboard. Every time you upload a fresh Shopify export, the segments refresh automatically — giving your marketing team a live view of customer health without recurring manual work.

You askedGenerated in 4.2s

"Run an RFM analysis on my customer base and show me the distribution of customers across segments."

Total

12,840+9.2%

Average

324+4.1%

Top segment

38%+2pp

Bar chart: customer count by RFM segment

Last 12 mo
Segment ASegment BSegment CSegment DSegment ESegment F

Table: top 10% LTV customers — lifetime value and first-purchase product

Table: dormant customer reactivation list — customer ID, email, LTV, days since last order

A dashboard built in AnalityQa AI — from question to chart, no SQL.

Real examples

Paste your data. Ask. Ship.

You

Run an RFM analysis on my customer base and show me the distribution of customers across segments.

AI

AnalityQa AI AI computes recency (days since last order), frequency (number of orders), and monetary value (total spend) for every customer, scores each dimension into quintiles, and assigns a composite RFM segment. It returns a distribution chart showing how many customers fall into each segment.

Bar chart: customer count by RFM segment
You

Who are my top 10% customers by lifetime value, and what was their first purchase product?

AI

The system ranks customers by total lifetime spend, isolates the top decile, and joins with order records to identify each customer's first-ever purchase product. Results are returned as a table showing customer ID, LTV, and first-purchase product.

Table: top 10% LTV customers — lifetime value and first-purchase product
You

Give me a list of dormant customers — at least 2 orders but no purchase in the last 120 days — sorted by lifetime value, ready to export.

AI

AnalityQa AI AI filters customers with two or more historical orders and no order in the trailing 120 days, sorts them by descending lifetime spend, and returns a CSV-ready table. You can download it directly and upload to your email or CRM platform.

Table: dormant customer reactivation list — customer ID, email, LTV, days since last order
You

How does average order frequency differ across my RFM segments?

AI

The system groups customers by RFM segment and computes average order frequency — orders per year — for each group, returning a bar chart that makes the behavioural difference between segments visually clear.

Bar chart: average order frequency by RFM segment
You

Compare the 12-month LTV of customers acquired through paid social versus organic search.

AI

AnalityQa AI AI joins your acquisition-channel data (from a UTM or CRM export) with order history, then computes 12-month cumulative revenue per customer for each acquisition channel and presents the cohorts side by side.

Line chart: 12-month cumulative LTV — paid social vs. organic search cohorts

What teams get out of it

✓Marketing teams build their first data-driven VIP segment within hours of uploading a Shopify export, without waiting for analyst support.
✓Dormant-customer reactivation campaigns are sent to a precisely filtered list rather than a broad re-engagement blast, improving conversion and reducing unsubscribes.
✓RFM analysis that previously required a data analyst and several days of work is completed in a single chat session.
✓Customer health metrics — active customers, dormant rate, LTV by cohort — are tracked on a shared dashboard instead of being recalculated ad hoc each quarter.

Frequently asked questions

Does AnalityQa AI AI work with Shopify and WooCommerce customer data?+

Yes. Both platforms export order history as CSVs that include customer identifiers, purchase dates, and order values — the inputs needed for RFM and LTV analysis. AnalityQa AI AI reads both formats without manual schema mapping.

Can I run customer segmentation across multiple Shopify stores?+

Yes. Upload order exports from each store in the same session. You can analyse each store's customer base separately or merge them into a unified view — for example, to identify customers who have purchased from more than one of your stores.

How is recency calculated — from the last order date or the last activity date?+

By default, recency is calculated from the last order date in your dataset. If you have other activity signals — such as a last-login date from a CRM export — you can upload that file and ask AnalityQa AI AI to use it instead. You can also specify a custom reference date in the chat.

How fresh are the customer segments?+

Segments reflect your most recent data upload. If you upload a fresh Shopify export weekly, your RFM dashboard updates weekly. There is no live Shopify API connection at this time, so the cadence of freshness matches your upload cadence.

How is customer data handled?+

You can delete all uploaded data from account settings at any time. For customer lists containing names or email addresses, we recommend pseudonymising before upload where possible — using customer IDs rather than raw email addresses for the analysis, and adding contact details only to the export used for campaign delivery.

Do I need SQL or data skills for RFM analysis?+

No. AnalityQa AI AI handles the aggregation, scoring, and segmentation in response to plain-English questions. If you want to adjust the scoring methodology — for example, 'weight monetary value more heavily in the composite score' — you can specify that in the conversation.

What plan do I need for customer segmentation with multiple data sources?+

Joining order data with a CRM or email export requires the Pro plan, which supports multi-file sessions. The Pro plan also includes dashboard pinning, so your team can monitor customer health metrics on an ongoing basis. Single-file RFM analysis from a single Shopify export is available on the Starter plan.

Related guides

E-commerce

E-commerce Sales Analysis Without the Spreadsheet Chaos

SaaS / Customer Success

Customer Churn Analysis Without the Spreadsheet Grind

Your data has answers. Start asking.

Upload a file or connect your database. Your first dashboard, in under 5 minutes.

Try AnalityQa AI AI free →

No credit card required

AnalityQa

Le workspace tout-en-un pour les data analysts et engineers.

Produit

  • Fonctionnalités
  • Tarifs
  • Blog
  • Outils gratuits

Société

  • À propos
  • Contact

Légal

  • Confidentialité
  • CGU

© 2026 AnalityQa AI. Tous droits réservés.

Tous les systèmes opérationnels