EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3421. Predicting price fluctuations of commodities by the joint use of extreme value techniques and machine learning methods: a case study of cherry price forecast
Invited abstract in session MC-12: Agrifood supply chain decision problems, stream OR in Agriculture and Forestry .
Monday, 12:30-14:00Room: 13 (building: 116)
Authors (first author is the speaker)
| 1. | Myriam Gaete
|
| Doctorado en Sistemas de Ingeniería, Faculty of Engineering, Universidad de Talca | |
| 2. | Marcela C. Gonzalez-Araya
|
| Department of Industrial Engineering, Universidad de Talca |
Abstract
Predicting export product prices is important for export companies for negotiating contracts with the associated participants of the supply chain. In this study, extreme value techniques are used for normalizing data of price fluctuations, and then, machine learning methods are applied for estimating future price fluctuations. This methodology is applied to a case study for estimating the export price of sweet cherries. The results show low error in the price fluctuations’ forecast, with a MSE lower than 1. Besides the good performance, the proposed methodology is easy to implement and can be executed in a low computational time by using personal computers.
Keywords
- Machine Learning
Status: accepted
Back to the list of papers