COMPARATIVE OF FORECASTING MODELS: CLASSICAL, BAYESIAN, AND COMBINATION TECHNIQUES
In the food industry, inventory models that provide adequate prediction of demand are useful for optimum supply management, especially in perishable products such as dairy products, because of their short shelf life and the importance of their quality related to health. However, some small and mediu...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | Spanish |
| Published: |
Universidad Nacional de Colombia, sede Medellín
2017-07-01
|
| Series: | Revista de la Facultad de Ciencias |
| Subjects: | |
| Online Access: | https://revistas.unal.edu.co/index.php/rfc/article/view/66085 |
| Summary: | In the food industry, inventory models that provide adequate prediction of demand are useful for optimum supply management, especially in perishable products such as dairy products, because of their short shelf life and the importance of their quality related to health. However, some small and medium Colombian companies do not have the technology and capabilities to do forecasts of their products, which is very important for production and inventory planning. In this paper we propose a comparison of the precision of forecasts of individual statistical models and combinations between them, using a multi-product algorithm for the combinations applied to a case study of sales of the dairy sector. It is found that an individual model of Bayesian regression with innovation is a very good alternative in the case studied, as well as two of the combination techniques used. |
|---|---|
| ISSN: | 0121-747X 2357-5549 |