The rise of open-source software and the widespread adoption of programming languages such as Python has allowed supply chain practitioners to work with increasingly more advanced statistical models. However, many professionals still have the impression that implementing advanced forecasting techniques is an insurmountable challenge that’s best left to other, more specialised professionals.
In this week’s episode, we are joined by Nicolas Vandeput, a Supply Chain Scientist specialized in demand forecasting and inventory optimization. As well as having a strong background managing a multinational supply chain, Nicolas is also passionate about education. As such he has spent time teaching at the Université Libre de Bruxelles.
In this episode, we talk about his new book: “Data Science for Supply Chain Forecast”, which aims to show that putting this new technology in place is much easier than one could think and how actually anyone can create their own advanced forecasts with the right tools and approach.
Machine Learning comes with a whole array of distinct questions when compared to “old school statistics”. It requires a different mindset, different experiments and different data. Joannes Vermorel joins us to discuss how going from a statistical forecast to a Machine Learning forecast will change some of our habits.
We understand how open-source software fits into Lokad’s vision and discuss the benefits of collaboration and competition. To finish the episode, we try to understand what the open-source supply chains of the future could look like and the first steps that executives can take to start implementing advanced forecasts for their organisations.
00:33 Nicolas, how did you get involved in the world of supply chains?
01:22 What is your book “Data Science for Supply Chain Forecasts” about?
01:58 Joannès, what’s your perspective on the book?
06:08 It’s not just the forecasting world benefitting from open source software. Which other industries have really benefited?
10:37 Does it make you nervous that there are so many easy to use, open source forecasting tools out there?
14:23 A lot of these ideas have been developed from a theoretical perspective. Could they be applied in a production setting?
15:33 For using these ideas on a daily, production basis how could Lokad help?
21:30 What do we do to evangelize the market so that there’s more importance placed on having the correct data?
24:15 Nicolas, we’ve spoken about the benefits of some of these open source toolkits, what are some of the drawbacks?
25:17 Joannès, you seem confident that there’ll always be a place for Lokad. Looking forward, what can you see that place being in the market?
31:59 Nicolas, what are your hopes for the readers of your book and for the use of open source toolkits going forwards?