Improve poultry farm efficiency in Iran: using combination neural networks, decision trees, and data envelopment analysis (DEA)

Since, poultry meat farming sub-sector has high potential for enhancing the agricultureindustry in comparison to other sub-sectors. therefore, evaluation of decision making units (dmus)of poultry in provinces and hence improving them is important task to the whole agriculture. besides,there exist several proposed approaches to resolve this problem. however, a different methodology isproposed due to its powerful discriminatory performance, in this research. for this purpose,combination of data envelop analysis (dea) and requisite data mining techniques same as artificialneural network (ann) and decision tree (dt) are employed in order to enhance the power ofpredicting the dmus evaluation performance because of their well-known efficiency, and thereby topresent precise decision rules for improving their efficiency. to illustrate the proposed model, allpoultry companies in iran were taken into account. however, in this case there is a small dataset andbecause the large dataset is necessary to collect data as well as to apply data mining methodology, so,we employed k-fold cross validation method to validate our model. consequently, applied model issupposed to predict efficiency of dmus and thereby to present decision rules in order to improve theefficiency precisely and accurately according to used optimizing techniques.