A labeled dataset with categorical and numeric features and a binary target — ready for logistic regression, trees and gradient boosting.
This is a free, reproducible E-commerce dataset you can generate and download right here as CSV, Excel, JSON or SQL. It is built for binary classification, model comparison and feature engineering — and because every field is correlated rather than random, the numbers actually hold together when you analyze them.
Shoppers carry RFM-style segments that set purchase frequency and behavior, and demand flows through a seasonality curve with weekend lifts and a Q4 holiday peak — so RFM, cohort, attribution, and seasonality analysis all return meaningful results.
Schema for the E-commerce export (the anomaly column appears only when labels are switched on):
| Column | Type | Description |
|---|---|---|
| order_date | date | Day the order was placed. |
| order_id | integer | Order id; lines in an order share it. |
| customer_id / customer | int / text | The shopper. |
| segment | text | RFM-style: Champion, Loyal, Regular, New, At-Risk. |
| channel | text | Acquisition channel. |
| product / category | text | SKU and department. |
| quantity / unit_price | number | Units and list price. |
| discount_pct | number | Promo or loyalty discount. |
| line_total | number | quantity x price x (1 - discount). |
| returned | 0/1 | Whether the line was returned. |
| anomaly | 0/1 | Present with labels on; flags fraud-like orders. |
import pandas as pd
df = pd.read_csv("ecommerce_orders.csv")
df.head()Around 12,000 rows by default. Change the row count in the generator above and re-export — anything up to ~200k works in the browser.
CSV, Excel (.xlsx), JSON, and SQL (a CREATE TABLE plus INSERT statements). Pick whatever fits your workflow.
Yes — an anomaly column flags a small fraction of rows (fraud-like / outlier events), so you have ground truth for classification and anomaly detection.
Yes. This page uses the fixed seed classif-demo, so the download is byte-identical on every machine. Clear the seed in the generator for fresh random data.
Yes. Use Tables → Excel/SQL for a normalized multi-table export, switch on Messy / dirty data in Advanced options for nulls, typos and inconsistent dates, and choose CSV, Excel, JSON or SQL on any download.
No — it is 100% synthetic, generated in your browser, with no real people or companies. Free to use commercially.