Analyze Customer Purchase History from Your Export
Purchase history exports from Shopify, WooCommerce, Magento, and point-of-sale systems contain every transaction but no summary of customer behavior. This analyzer calculates repeat purchase rate, average order frequency, product pairs bought together, and cohort retention without pivot tables or formulas.
Upload your purchase history CSV and see repeat rate, product affinity, and cohort retention calculated from the raw transactions.
Drop your file in and ask a question — no account needed.
Upload your spreadsheet.xlsx .xls .csv — free to try, no accountWhat this export contains
| order_id |
| customer_id |
| order_date |
| product_id |
| product_name |
| quantity |
| unit_price |
| total_amount |
| customer_email |
| order_status |
| payment_method |
| shipping_country |
Common questions
How do I calculate repeat purchase rate from order history?
Group orders by customer_id and count how many customers have more than one order. Repeat rate is (customers with 2+ orders / total customers). The analyzer does this grouping automatically and shows the distribution of 1-time, 2-time, 3+ buyers.
What file format does purchase history need to be in?
CSV or Excel exports from any ecommerce platform work as long as each row is one line item and columns include order_id, customer_id, order_date, and product_id or product_name. Multi-sheet workbooks are flattened on upload.
Can I analyze which products are frequently purchased together?
Yes. The analyzer groups line items by order_id to find product pairs, then counts how often each pair appears across all orders. This is market basket analysis and it works on purchase history files of any size.
How is cohort retention calculated from transaction data?
Customers are grouped by the month of their first order (their cohort), then each subsequent month shows what percentage of that cohort made another purchase. This requires joining each order back to the customer's first order date, which the analyzer handles automatically.
Does this work with refunds and canceled orders in the data?
Filter by order_status before analysis to exclude refunded or canceled transactions. The analyzer preserves all rows so you can compare metrics with and without those statuses included.
Try it with your own file
DataMimi reads the file you actually have — merged cells, headers below row one, totals pasted at the bottom — and shows which rows and columns every number came from.
Ask about your file