Evaluation of artificial neural networks as a model for forecasting consumption of wood products

In specific sciences, such as forest policy, the need for anticipation becomes more urgent because it has to manage valuable natural resources whose protection and sustainable management is rendered essential. In this paper, a modern method has been used, known as artificial neural networks (ANNs). In order to forecast the necessary future volumes of timber in Greece, a neural network has been developed and trained, using a variety of time series derived from the database of the Food and Agriculture Organisation of the United Nations (FAO) (concerning Greece) as external values and as internal value the Consumer Price Index has been used. Comparing the results of this project with linear and non-linear econometric forecasting models, it has been found that neural networks correspond, as confirmed by the econometric indicators MAPE (average absolute percentage error) and RMSE (the square root of the percentage by the average sum of squares differences).