EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
2282. Coherent forecasting for Supply Chain Optimisation
Invited abstract in session WC-57: Forecasting for the middle mile, stream Optimization at Amazon.
Wednesday, 12:30-14:00Room: S06 (building: 101)
Authors (first author is the speaker)
| 1. | Hermina Petric Maretic
|
| 2. | Sidharth Gupta
|
| Amazon | |
| 3. | Juba Nait Saada
|
| Amazon | |
| 4. | Chris George
|
| ATS, Amazon |
Abstract
The precision of planning and decision making in Amazon is heavily reliant on sophisticated forecasting methods. These forecasts, often made independently, enable different aspects of logistic chain, such as truck scheduling or labor planning. However, in reality, they forecast values that often interact or depend on each other, or in the least contain strong correlations. We explore various methods to take these relationships into account, such as hierarchical reconciliation, combinations of forecasting and simulation, modelling input-output system constraints, as well as joint time series forecasting approaches based on diffusion models.
Keywords
- Forecasting
- Machine Learning
- Supply Chain Management
Status: accepted
Back to the list of papers