Federated Demand Forecasting for Retail Supply Chains
International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064

Federated Demand Forecasting for Retail Supply Chains

Jatin Singh, Rahul Khurana

Abstract: Retailers, distributors and store operators all forecast demand for the same products, but almost none of them will hand their sales history to one another. Federated learning offers a way around that stalemate: each party trains on its own data and shares only model updates. The question we care about is a practical one. Does federation actually make store-level forecasts better, and does it still help once the updates are protected with differential privacy? We study this on the public M5 dataset (30,490 SKU-store series from ten Walmart stores in three US states, 1,969 days), treating every store as a separate data silo. We compare local-only training, a pooled centralized model, FedAvg, FedAvg with local fine-tuning, and a DP-FedSGD variant that guarantees item-level (ε, δ)-differential privacy for each store's catalogue, with privacy computed exactly using Gaussian differential privacy. The answer depends mostly on how much history a store has. With two years of training windows, federation is close to a wash at the SKU level (FedAvg with fine-tuning scores 0.895 WRMSSE against 0.899 for local training) and its 4.2% reduction in store-total error is within seed noise. With only two weeks of windows, local models fall apart and federation recovers much of the loss (0.939 vs 0.971), yet a plain 28-day moving average (0.922) is still hard to beat. When one newly opened store joins nine mature ones, fine-tuning the federated model lowers that store's error by 7.5% on average over local training, and by 7.1% with ε = 2 privacy. We also report where the approach breaks: near-zero sales on Christmas Day, erratic SKUs, and private training when stores drop out of rounds. The full set of experiments runs in under half an hour on two CPU cores, and every number in this paper comes from our own runs.

Keywords: federated learning; retail demand forecasting; differential privacy; cross-silo learning; SKU-level forecasting; M5 dataset

How to Cite?: Jatin Singh, Rahul Khurana, "Federated Demand Forecasting for Retail Supply Chains", Volume 15 Issue 11, November 2026, International Journal of Science and Research (IJSR), Pages: 775-780, https://www.ijsr.net/getabstract.php?paperid=SR261111062849, DOI: https://dx.doi.org/10.21275/SR261111062849

Download Citation: APA | MLA | BibTeX | EndNote | RefMan

Share This Research

Help this article reach readers, researchers and professionals.

Share activity is measured for research-engagement analytics. Only verified, unique public shares can support award tie-breaking.

Confirm Your Share

Enter your details so IJSR can confirm this sharing activity.

Your details are used to validate this share and protect the award process from duplicate or false activity.

Download Article PDF


Rate This Article!

Top

Confirm Your Share

Enter your details so IJSR can confirm this sharing activity.

Your details are used to validate this share and protect the award process from duplicate or false activity.