Mohamed, Ahmed Ramzy2022-05-192022-05-192022-05https://doi.org/10.1007/s40953-022-00297-9http://repository.msa.edu.eg/xmlui/handle/123456789/4948This paper discusses a new representation for the efciency frontier method through a proposed algorithm for augmented feed forward back propagation neural network models, in order to estimate the economic performance, and the efectiveness of macroeconomic policies in Egyptian economy, by using a quarter time series data from 1990Q1 to 2019Q2. In this study I developed artifcial neural network mod- els—ANN—corresponding with the conditions of the Egyptian economy, by build- ing an optimal efciency frontier and then comparing the actual performance of the Egyptian economy with that limit, which includes the lowest possible variations for both infation and output. As for the new contribution of this study, it is designated to calculate the optimal infation rate and the optimal output level in the Egyptian economy through a model, which combines the higher predictive power of feed for- ward neural network models and the high explanatory power of a stationary or ran- dom walk stochastic models, in order to obtain the ftted values of the optimal out- put level, in addition to the optimal infation rate. It is clear from the results of the study, the extent of the essential congruence between the actual Egyptian economic performance during the study period and the economic performance index that was built via the new contribution of this study.en-USArtifcial Neural Network Models Efciency Frontier MethodNew Loss FunctionEconomic Performance IndexArticlehttps://doi.org/10.1007/s40953-022-00297-9