Deep learning for agricultural products price forecasting: the case of Ecuador

The application of forecasting techniques in the agriculture industry started with an agricultural commodity prediction almost a century ago. However, currently, the same application is not at all explored in the same field. For instance, in the Ecuadorian context, farmers have to suffer the volatility of prices of agriculture products during all the growing stages since they do not count on any forecasting method for preventing future events. Under this context, to the best of our knowledge, there is no study that focuses on forecasting agricultural prices despite the fact that the ministry of agriculture and livestock (MAG) has recorded the prices of agricultural products since 2010. Therefore, this work aims to reduce the gap of knowledge by presenting a pioneer implementation of five deep learning algorithms which forecast weekly and monthly prices of avocado and red onion from the wholesale market of Ibarra city in Ecuador. Results have shown that single models are still suitable for forecasting, although, the best performance comes from compound models as Conv-LSTM MLPs. Likewise, with proper hyper-parameter tuning, the last model showed an error reduction (MAE) of 23% for weekly avocado prices.

• Príomhchruthaitheoir: Noboa Chávez, Sherald Damián (author)
• Formáid: bachelorThesis
• Teanga: eng
• Foilsithe / Cruthaithe: 2021
• Ábhair: Predicción productos agrícolas; Aprendizaje profundo; Ajuste de hiperparámetros; Ecuador; Commodity forecasting; Deep learning; Hyper-parameter tuning
• Rochtain ar líne: http://repositorio.yachaytech.edu.ec/handle/123456789/456