Fordel StudiosDemand Forecasting for FMCG Distribution
This case study describes a real engagement. Client identity, proprietary details, and specific metrics are anonymized or approximated under NDA.
What needed
solving
Inventory stockouts running at 8% and overstock waste at 14%. Demand planning was based on spreadsheet extrapolation and category manager intuition — no systematic use of sales history, seasonality, or external signals. SKU-level accuracy was insufficient for procurement planning.
FMCG demand data is structurally messy. Sales history contained gaps from stockout periods (where zero sales reflected supply constraints rather than zero demand), promotional events that created artificial spikes, and distributor bulk-buy patterns that had no relationship to end consumer demand. Cleaning and feature engineering this data correctly — distinguishing genuine demand signal from supply-side and channel artifacts — was more work than the modeling itself. Seasonal patterns in the portfolio varied significantly by category, requiring per-category feature sets rather than a single global model. External signals (regional festivals, school calendars, weather) were relevant for some categories but not others, requiring feature selection to avoid overfitting.
How we
built it
- 01
Audited the existing spreadsheet forecasting process to understand which signals category managers were using intuitively — promotions, seasonality, regional variation — and formalised these as model features rather than replacing human judgement with a black box.
- 02
Built separate models for different SKU velocity tiers rather than a single universal model, since fast-moving staples and slow-moving specialty products have fundamentally different demand patterns that a single model handles poorly.
- 03
Integrated external signals — regional weather, promotional calendars, competitor pricing data — that the spreadsheet process couldn't incorporate systematically.
- 04
Set up a performance monitoring dashboard that gave category managers visibility into forecast accuracy by SKU and region, building trust in the model output before requiring procurement decisions to follow it.
This engagement replaced a spreadsheet-based demand planning process with a production ML forecasting system covering 1,200+ active SKUs across 8 distribution zones. The system was built as a weekly batch pipeline using Airflow for orchestration, with Metabase dashboards surfacing forecasts and accuracy metrics to category managers. Integration with the existing ERP procurement module was done via CSV export initially, with a REST API endpoint added in week 7 to support direct import. The forecasting models are retrained weekly on rolling 24-month sales history, with automatic fallback to the previous model version if retraining degrades validation metrics.
What we
delivered
ML pipeline ingesting sales history, seasonal patterns, and external signals to produce SKU-level demand forecasts at weekly and monthly horizons, integrated into the procurement planning workflow.
Measurable
outcomes
- Demand forecast accuracy improved 34% on a mean absolute percentage error basis, with the largest gains on the historically hardest-to-predict seasonal SKUs.
- Inventory stockouts reduced 61%, with the improvement concentrated in the SKU categories where forecast variance had been highest.
- Overstock waste reduced 23% as procurement decisions became based on demand signals rather than safety stock instinct.
“The stockout reduction was measurable within the first planning cycle. Category managers were sceptical initially, but the forecast accuracy on the products that had historically been hardest to predict won them over.”
— Head of Supply Chain Planning, FMCG DistributorReady to build
something like this?
Tell us what you are building. We will scope it, price it honestly, and give you a clear plan.
Start a ConversationFree 30-minute scoping call. No obligation.