Global Construction LeaderDemand forecasting and supply chain

Demand forecasting more than twice as accurate for new product launches

A new product has no sales history, so ordering was done on experience and estimates. A global market leader in construction tools wanted to improve demand forecasting for new products. Our calculation model took accuracy from 40% to 86%.

Demand forecasting more than twice as accurate
for new product launches
  • 86%Forecast accuracy, up from 40%
  • CHF 778,000Saving per year
  • 85%Less manual work
  • 1,247Products analyzed
Sector
Supply Chain
1Background

The challenge

This global leader in professional construction tools faced a complex challenge when launching new products. Usual forecast methods did not work for products without sales history. This led to either too much stock or missed sales because a product was not in stock.

Key problems

  • 01No sales history available for new products
  • 02Too much stock because demand was overestimated
  • 03Missed revenue from underestimation and products that were not in stock
  • 04Manual forecasts were time-consuming and inconsistent
Vol magazijn met voorraad in de stellingen
2Methodologie

Our approach

We developed a calculation model that combines product characteristics, market figures, and comparable product launches into an accurate prediction for new products.

  1. 01

    Bringing the figures together

    We brought product data, market trends, seasonal patterns, and figures from earlier launches together in one overview.

  2. 02

    What predicts a launch

    We worked out which characteristics predict a launch: how much a product resembles existing products, how big the market is, and which existing product will sell less because of it.

  3. 03

    Letting the model learn

    We let several calculation models practise on earlier product launches and tested them on launches they had not seen. The one that was right most often became the model.

  4. 04

    In use in planning

    The model runs in the planning systems and is updated automatically, so the prediction moves with the market.

3ImpactSupply Chain

Results

The new forecasting solution delivered results within 6 months of implementation.

  • 2.1xAs accurate as beforeFrom 40% to 86% forecast accuracy for new product launches
  • 85%Reduction in manual workForecasters now focus on strategy instead of data entry
  • 3 weeksFaster to marketThrough better supply chain and distribution planning

Interested in this case?

Leave your email and we'll reach out to discuss how we can achieve similar results for your business.

Rutger Geerlings, solution architect at Stratalytic

Rutger Geerlings

Solution architect

What is it about?

No sales pitch, no newsletter. We only use your details for this conversation.

Thirty minutes to see where the biggest impact is.

An honest estimate in numbers, even if the answer is that it does not pay off.