The inventory optimization of a large manufacturing multi-echelon supply chain requires probabilistic forecasts. These forecasts are used to assess the consequences of every single stock movement and every single production capacity adjustment within the supply network.
With around 180 manufacturing plants and business presence in more than 150 countries, Bridgestone is the largest manufacturer of tyres in the world. In this special episode of LokadTV, we are lucky enough to take a peek behind the scenes and understand the daily operations and challenges that are faced by a multinational corporation such as Bridgestone. We welcome Nicolas Vandeput to discuss the recent project completed between Lokad and Bridgestone to improve their European supply chain operations.
We discover how things were managed before the arrival of Lokad, whith multiple teams in multiple countries fighting to get as much stock as they could in order to avoid stockouts in their own country. We discuss why our tailor-made and programmatic approach proved to be the best option in the market for such a multi-echelon network.
With a multitude of locations around Europe, from Latvia all the way to Portugal, and up to 60 000 SKUs, the Bridgestone supply chain is inherently complex. We explore the difficulties that are introduced when tackling a multi-echelon problem and discuss how a company, which places such huge emphasis on lean stock management, battles daily to service their customers as efficiently as possible.
Finally, we understand the challenges of implementing a project such as this across such a diverse organisation and we learn how the change management process was approached with minimal impact to daily operations.
00:28 Nicolas, I guess a nice place to start would be to illustrate the scale of the project and the supply chain at a multinational corporation such as Bridgestone. So how many SKUs and locations are we talking about?
01:40 With such a multitude of locations around Europe, from Latvia all the way to Portugal, what are the complexities that are introduced?
02:20 What was the initial idea behind the project? How did it start?
03:28 What was so different about the approach Lokad was taking?
06:13 What are the key difficulties that this introduces?
08:26 Knowing the inherent complexity behind the Lokad solution, how did you approach that change? Were people really interested in it?
11:18 The project finally went live back in March 2018. What were the initial challenges that we faced?
14:33 How did you take that noise and translated it into a probabilistic forecast?
16:55 How did the project get implemented? What were the initial results? What did we have to change and adapt as the project went on?
19:09 Nicolas, what sort of evolutions have you seen over the course of the project?
20:33 How about the impacts of the project on, for example, the IT infrastructure? Are there any changes that have actually been made on the daily operations?
21:36 From Lokad’s perspective, what have we learnt from implementing such a multi-echelon project?
24:14 What are your key takeaways from this project? What are the key results?