An Early Warning Method for Basic Commodities Price Based on Artificial Neural Networks

The prices of products belonging to the basic family basket are an important component in the income of producers and consumer spending; its excessive variations constitute a source of uncertainty and risk that affects producers, since it prevents the realization of long-term investment plans, and can refuse lenders to grant them credit. His study to identify these variations, as well as to detect their sources, is then of great importance. The analysis of the variations of the prices of the basic products over time, include seasonal patterns, annual fluctuations, trends, cycles and volatility. Because of the advance in technology, applications have been developed based on Artificial Neural Networks (ANN) which have helped the development of massive sales forecast on consumer products, improving the accuracy of traditional forecasting systems. This research uses the RNA to develop an early warning system for facing the increase in basic agricultural products, considering seasonal factors.

• Autores: Silva, Jesús; Varela, Noel; Martínez Caraballo, Hugo; García Guiliany, Jesús; Cabas Vásquez, Luis Carlos; Navarro Beltrán, Jorge; León Castro, Nadia
• Tipo de recurso: http://purl.org/coar/resource_type/c_816b
• Fecha de publicación: 2019
• Institución: Corporación Universidad de la Costa
• Repositorio: REDICUC - Repositorio CUC
• Idioma: eng
• OAI Identifier: oai:repositorio.cuc.edu.co:11323/5133
• Acceso en línea: https://hdl.handle.net/11323/5133; https://repositorio.cuc.edu.co/
• Palabra clave: Forecast; Multiple Input Multiple Output; Multilayer perceptron; Predictive model; Cyclic variation; Support vector machines
• Rights: openAccess
• License: CC0 1.0 Universal