Spaces:
Running on Zero
Running on Zero
|
Download README.md from EquilStable/MarginGraph: direct link, hf CLI and curl.
- Browser
- Download file 1.13 kB
-
https://huggingface.co/spaces/EquilStable/MarginGraph/resolve/main/README.md
- Command line
-
hf download hf://spaces/EquilStable/MarginGraph/README.md
-
curl -L -o README.md https://huggingface.co/spaces/EquilStable/MarginGraph/resolve/main/README.md
1.13 kB
A newer version of the Gradio SDK is available: 6.32.0
metadata
title: MarginGraph
emoji: 🛒
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 6.30.0
python_version: '3.13'
app_file: app.py
pinned: false
license: mit
short_description: Checkout add-ons that sell and keep your margin
MarginGraph demo
Profit-aware checkout add-on recommendations. Stage 1 (EASE co-purchase model) finds what customers are likely to add; Stage 2 picks at most 2 add-ons that maximize expected profit under hard rules (margin floor, in stock, overstock push).
- Demo store: 2,000 real products from UCI Online Retail II. Costs and stock are simulated.
- Your store: upload
products.csv(item, description, price, unit_cost, stock, overstock) and optionallyorders.csv(order_id, item) to train on your own data in about 2 seconds. - Batch: upload open baskets, download recommendations as CSV.
- Backtest: measured numbers on held-out Oct to Dec 2011 invoices.
Runs on the free CPU tier (about 250 to 350 MB RAM). Source:
https://github.com/Sanskar1724/MarginGraph (folder space/).
Rebuild the artifacts: python space/build_artifacts.py --xlsx online_retail_II.xlsx