Skip to main content

Project - Agri-food

Production-Market Optimisation

The challenge

Optimising production and transportation costs is a major challenge for any company operating on a global scale. In the present case, the company concerned has more than 40 factories all over the world. Each factory manufactures some, but not all, of the company’s products. Each factory has different variable costs. Depending on the country of origin and destination, transport costs (before and during transport) vary, as does the customs rate.

The challenge, in this situation, is therefore obvious: how to optimally distribute the production of products in order to minimise operational costs, taking into account all these factors (production, transport, customs)

The solution

In this case, the solution can be divided into two phases. In a first phase, we can develop a tool that allows to calculate the full production costs by combining all the available information: the operational costs of the factories, the combination of customs costs between the products, the origins and the destinations and the costs of transport (estimated). This tool is then a query tool, making it possible to estimate the optimal sourcing strategy for a product in a specific destination. Depending on the level of data maturity and business integration, this first phase can be simple or laborious (no unified database between factories, departments, etc.) In any case, it is crucial to define a clear information structure and recover all existing data, wherever it is held.

Once this query tool has been developed, the second phase consists in adding a dynamic and proactive layer. This comes in the form of artificial intelligence, a recommendation mechanism that suggests optimal sourcing strategies for the coming months, based on a provided sales forecast. The recommended optimal sourcing strategies can be optimised based on various criteria, such as total cost, CO2 emissions (due to transportation), similarity to current situation, minimum factory occupancy, etc.

The potential gain

In many cases, the first phase of this solution already sheds a very interesting light on production costs and the impact of various factors on the final cost. This is already helping to guide future operational decisions.

In the second phase, the return on investment depends on the optimisation criteria chosen. If sourcing is optimised only on the criterion of total cost, it can induce vast adaptations of sourcing compared to current situations, which translates into reductions in operational costs.


Project Details

Client Activity

  • Agri-food industry

Solution Brand

  • Microsoft
  • Power BI
  • Azure
  • Python

Nature of the work carried out

  • Resource Optimisation
  • S&OP


  • Data Science Offline and Optimisation

Notre ThinManager-Integrator Certified

1.22 Mb – file pdf
Download this file

Other references More to be discovered

Let's stay in touch

Subscribe to our newsletter