Ranchi Dukaan Pro — Predicting Stock Demand with TabPFN-TS

Description and use

Ranchi Dukaan Pro is a prototype that uses TabPFN‑TS to forecast 7‑day demand and compute restock recommendations for small retailers.

Problem

Small retailers need to decide what to reorder, how much inventory to keep, and when to place orders. Too little stock can mean missed sales, while excess inventory can tie up cash and increase the risk of expiry or waste.

Outcome

The prototype forecasts 134 Milk units, 96 Bread units, and 49 Rice units over seven days, suggesting reorder quantities of 13, 9, and 1 units respectively, with a total estimated cost of ₹616. Adjusting inventory inputs changes recommendations accordingly. TabPFN‑TS achieved lower MAE and WAPE than a simple weekday‑baseline in a synthetic holdout test, though Bread performed better with the baseline.

Workflow

• Load daily sales history for each product
• Use TabPFN‑TS to generate a seven‑day demand forecast
• Estimate demand during the supplier’s lead time
• Combine that estimate with current stock, incoming stock, and safety stock
• Display a suggested reorder quantity and its estimated cost

Evidence

I built Ranchi Dukaan Pro, a prototype that uses TabPFN-TS to estimate product demand over the next seven days and combine those estimates with simple inventory rules.

Source

Reorder quantity = max(0, lead-time demand + safety stock - current stock - incoming stock)

Source

TabPFN-TS MAE 1.29 vs Baseline MAE 1.62; TabPFN-TS WAPE 9.18% vs Baseline WAPE 11.56%

Source

This is an educational and hackathon prototype, not a production inventory system.

Source