Dead-Stock Predictor
Upload your sales history and the model predicts which items will sell nothing in the next 90 days, often while they are still selling a little. Add your stock file to see how much money is about to get stuck and what to do about it. Everything runs in your browser; your data never leaves this page.
1. Sales lines CSV
Date, product, quantity. Two years is best, at least one.
2. Stock CSV (optional)
Product, quantity on hand, unit cost.
Analysis date
Dates can be 2026-09-27, 27-09-2026, 27/09/2026 or 27-Sep-2026. Returns can be negative quantities.
Stock value by recommended action
Clear now: discount, bundle or return to supplier · Stop reordering: sell what you have, watch · Overstocked: still selling but more than 6 months of stock; reduce the next order.
| Product | Dead risk ▾ | Last 26 weeks | Last sale | Sold 13 wk (prev) | On hand | Value at risk | Action |
|---|