Logistics and data: towards a decision support tool
summary
Covers using data science to cut logistics costs and improve service—specifically inventory optimisation for maintenance parts by predicting consumption with predictive models, handling parts that need business rules, and how inventory managers choose and tune models (which parameters they examine). Also covers integrating the chosen model into the value chain and the need for human/business ownership to adapt model outputs to context.
AI-written summary · about
chapters (10)
- 0:00Intro
- 0:29Logistics is a cost centre
- 0:45There is a balance to be found between the stored value and the service rate
- 0:58Make a monthly prediction of demand and then a recommendation of inventory level
- 1:19What does stock consumption look like for maintenance parts?
- 1:44Given the particular type of stock consumption, the Croston model is the most appropriate
- 2:14Short introduction on how Croston model works
- 2:31Business knowledge makes it possible to add rules
- 3:21The business analysis of the generated models is fundamental to choose the optimal model
- 3:49The Al is not self-supporting in this case
related talks
27mOptimizing Omnichannel Order Fulfillment with AI and Advanced Analytics
23mArtificial Intelligence for Store Assistance
42mAugmenting Human Decision Making with Data Science
08mdata science in automotive
37mLife of a data scientist
38mOptimizing Retail Forecasting Through AI Models
16mUsing visualisations for addressing fleet management problems
28mThe Value of UX Applied to Company Data