Forecasting egg price in Iran: a comparison between Artificial Neural Networks and ARCH methods

  The age of poultry industry is as short as a few decades; however, it has a pertinent role in providing required protein of people. This reveals the fact that a precise forecasting of price in the poultry sector may result in optimized resource allocation, efficiency enhancement and an increase in income of the producers.   Regarding the importance of price forecasting of the protein products including egg, this research uses methods of ARCH and ANNs to forecast the egg price in Iran for the various time paths consisting of one month, six months and twelve months. Accordingly, the main hypothesis relies on the more efficiently of the ANNs than those of the ARCH methods. Monthly data are collected for the domestic resources related to the agricultural sector for the period 1992-2006. The empirical results obtained confirm that the performance of ANNs in forecasting has been more precise than that of GARCH in more times. The implication is that the use of ANNs in prediction of the egg price is able to affect policymakers in the poultry industry toward making better decisions in the market.   JEL classification: C45, Q11