Demand & inventory planning

The SupChains Way

Over the years, we developed our own way of doing demand and inventory planning. It is what we apply on every client project, and it is how the winning teams of the VN1 and VN2 competitions work too.

At its core: let a robust, global machine-learning engine do the mechanical forecasting work, ask planners to bring the information the engine cannot see, measure the value added at every step, and optimize inventory policies by simulation rather than trusting a formula.

13 practices
16 articles
1 folder to download

The SupChains Way in 13 practices

What we do on every project, and what we stopped doing.

Forecasting Engine

Run one global, bulletproof machine-learning engine
not statistical models tuned SKU by SKU
Forecast unbiased, unconstrained demand
not sales capped by shortages, not the budget
Forecast at the granularity your supply decisions need
not at the level the org chart asks for
One shared engine for all products
no ABC/XYZ classes choosing the model

Planners

Enrich only on real insight
no reviewing top products one by one, no tweaking models, no gut feeling
Fix data errors, model business events
no outlier detection, no trimming history
Budgets follow forecasts
no wishful thinking, no forecast editing to hit the budget or the target

Measuring success

Track the value added by every step (FVA)
not one final accuracy number
Track cumulative absolute error and Bias
not accuracy alone, never MAPE
Measure cumulative error over the risk horizon
not one arbitrary lag
Compare your accuracy vs. a moving average
do not focus on absolute accuracy, it doesn’t say much

Inventory Engine

Tune inventory targets by simulation on real demand and forecasts
not the textbook formula, not DDMRP
Set service levels by strategy, cost and risk
not by ABC class

Get the 16 articles behind these practices

The 16 articles as PDFs plus an AI-ready text file to paste directly into ChatGPT or Claude to discuss your own planning processes.

Leave your email and the download links appear right away on the next page. You also join our weekly learning path on demand and inventory planning and get invited to our webinars.

Your information is protected and we never spam. View our privacy policy.

The whole method in 34 minutes

How to run an efficient demand planning process

Want this applied to your supply chain?

SupChains delivers machine-learning demand forecasts and inventory optimization to manufacturers, distributors and retailers, and trains their planning teams. If your team is ready to change how it plans, let’s talk.

Let’s talk
−30%forecast error
−20%inventory