Time Series Isn’t Enough: How Graph Neural Networks Chang...

What’s Happening

Here’s the thing: Why modeling SKUs as a network reveals what traditional forecasts miss The post Time Series Isn’t Enough: How Graph Neural Networks Change Demand Forecasting appeared first on Towards Data Science.

Demand forecasting in supply-chain planning has traditionally been treated as a time-series problem. Each SKU is modeled independently. (and honestly, same)

A rolling time window (say, last 14 days) is used to predict tomorrows sales.

The Details

Seasonality is captured, promotions are added, and forecasts are reconciled downstream. And yet, despite increasingly sophisticated models, the usual problems persist: Chronic over-and under-stocking Emergency production changes Excess inventory sitting in the wrong place High forecast accuracy on paper, but weak planning outcomes in practice The issue is that demand in a supply chain is not independent.

As an example, this is what just 12 SKUs from a typical supply chain look like when you map their d plants, product groups, subgroups, and storage locations. So when demand shifts in one corner of the network, the effects are felt throughout the network.

Why This Matters

In this article, we step outside the model-first thinking and look at the problem the way a supply chain actually behaves — as a connected operational system. Using a real FMCG dataset, we show why even a simple graph-based neural network(GNN) fundamentally outperforms traditional approaches, and what that means for both business leaders and data scientists. A real supply chain experiment We tested this idea on a real FMCG dataset ( SupplyGraph ) that combines two views of the business: Static supply-chain relationships The dataset has 40 active SKUs, 9 plants, 21 product groups, 36 sub-groups and 13 storage locations.

As AI capabilities expand, we’re seeing more announcements like this reshape the industry.

The Bottom Line

From a planning standpoint, this network encodes institutional knowledge that often lives only in planners’ heads: “If this SKU spikes, these others will feel it. ” Temporal operational signals and sales outcomes The dataset has temporal data for 221 days.

Sound off in the comments.