Skip to content
Sebastian.Gebhardt

Delphine

ML Demand Forecasting for Footwear Retail

Multi-modal sell-through prediction for footwear: a photo of the shoe plus its attributes, and a buy/pass verdict before the season.

Deployed · GCP
VERDICTUNCERTAINTY BAND
Predicted sell-through, with calibrated uncertainty · AUC 0.723
Training rows
134.690
Out-of-sample AUC
0,723
Model features
105

The problem

Footwear buys are decided months before launch, looking at a photo and a spec sheet. Getting it wrong on the high side means clearing at negative margin; on the low side, missing the season.

How it works

A late-fusion neural network combines product photography (EfficientNet-B0) with categorical attributes — brand, model, material, color, gender, season — and numeric variables like price, and predicts weekly sell-through. The buyer works through a Telegram bot: send the photo, get the verdict with a calibrated uncertainty band.

What it does

  1. 01

    Genuinely multi-modal

    The product photo is a model input, not decoration: vision plus metadata in a single network.

  2. 02

    Verdict with uncertainty

    Buy or pass, with a calibrated uncertainty band — the model also says how confident it is.

  3. 03

    In the buyer's flow

    Telegram interface: the verdict arrives where the buyer already works, with no new system to learn.

Limits

0.723 out-of-sample AUC: the model ranks risk well, but does not replace the buyer's judgment on any individual decision. That is why the verdict ships with an uncertainty band.

Related projects

Last updated: August 2026

Run a retail operation and recognize the problem? The advisory side of this work lives at Menlo & Oak — and you can always write to me directly.

Advisory version All projects