Customer Clusters

Customer Clusters uses AI-powered segmentation to group your customers by spending behavior and purchase cadence. This gives you a clear view of who your highest-value buyers are, where churn risk sits, and how to allocate marketing and retention spend instead of working through flat customer lists.

The analysis is based on two dimensions:

• Average Order Value (x-axis) — How much the customer spends per transaction.

• Purchase Frequency (y-axis) — How often the customer makes purchases, measured per month.

Corgi automatically identifies natural groupings in your customer base and assigns each customer to a cluster. The scatter plot on the Clusters page visualizes every customer, color-coded by their assigned cluster, so you can see density, outliers, and boundaries at a glance.

The five customer segments

High-Value Customers

These are your most valuable customers: high spending, high frequency, top-right quadrant on the scatter plot.

• Characterized by above-average order values and high purchase frequency.

• Strategy: Prioritize retention, offer loyalty rewards, and ensure premium support.

Loyal Frequent Buyers

Regular customers with moderate spending but consistent engagement. They appear in the upper-left or mid-top area of the scatter plot.

• Purchase often, even if individual order values are modest.

• Strategy: Encourage upselling and cross-selling to increase AOV.

Price-Conscious Buyers

Budget-focused customers in the lower-left area who respond well to discounts and promotions.

• Tend to have lower order values and purchase less frequently.

• Strategy: Use targeted promotions and discount campaigns to drive repeat purchases.

New Explorers

Recent customers still evaluating your product. They sit in the bottom-middle to mid-right range.

• Low frequency with moderate order values.

• Strategy: Focus on onboarding, first-purchase follow-ups, and welcome campaigns to convert them into repeat buyers.

Dormant Customers

Previously active customers who have not purchased recently. They sit along the bottom of the scatter plot with near-zero frequency.

• Purchase history exists, but no recent activity.

• Strategy: Launch re-engagement campaigns, win-back offers, or surveys to understand why they left.

Reading the charts and cards

Cluster Summary Cards

Each cluster has a summary card showing four metrics:

Use the summary cards to compare segments numerically and identify which group is driving the most revenue.

Segment Performance

A combined bar and line chart shows the number of customers (bars) and total revenue (line) for each segment side by side. This makes it easy to see which segments have the most customers versus which contribute the most revenue.

Purchase Behavior by Segment

This chart compares average purchases per month and average order value across all segments. It helps you quickly identify which segments buy more often and which spend more per order.

The Scatter Plot

The main Clusters view plots every customer on Average Order Value (x) and Purchase Frequency (y). Each point is color-coded by its cluster assignment. Use it to identify dominant segments, think about natural boundaries, and spot outliers worth investigating.

Turning insights into action

A practical workflow for using Customer Clusters:

1. Open the Clusters page and look at the scatter plot to identify your dominant segments.

2. Check Segment Performance to confirm which clusters contribute the most revenue.

3. Drill into the Cluster Summary Cards for exact counts, averages, and frequency.

4. Use Purchase Behavior by Segment to compare the tradeoffs between high-frequency and high-AOV groups.

5. Act on each cluster using the recommended strategy for that segment.

Notes and limitations

• Small customer bases. Clusters may be less distinct with a small number of customers. Segmentation improves as transaction volume grows.

• Single-purchase customers. May cluster as New Explorers or Dormant depending on recency.

• Seasonal merchants. Purchase frequency can shift dramatically month to month. The clusters adapt automatically, but you should account for seasonality when deciding which segments to act on.

• New merchant onboarding. First-time users may see sparse or shifting clusters until enough transaction history accumulates.