No abstract

No abstract

No abstract

In the real world encountering with noisy and corrupted data is unavoidable. Auto industry sector (AIS) as a one of the significant industry encounters with noisy and corrupted data regarding to its rapid development. Therefore, developing the performance assessment in this situation is so helpful for this industry. As Data envelopment Analysis (DEA) could not deal with noisy and corrupted data, the alternative method(s) is very important. As one of excellent and promising feature of artificial neural networks (ANNs) are theirs flexibility and robustness in noisy situation, they are a good alternative. This study proposes a non-parametric efficiency frontier analysis method based on the adaptive neural network technique for measuring efficiency as a complementary tool for the common techniques for efficiency assessment in the previous studies. The proposed computational method is able to find a stochastic frontier based on a set of input-output observational data and do not require explicit assumptions about the function structure of the stochastic frontier. In this algorithm, for calculating the efficiency scores of auto industry in various countries, a similar approach to econometric methods has been used. Moreover, the effect of the return to scale of AIS on its efficiency is included and the unit used for the correction is selected by notice of its scale (under constant return to scale assumption). Another feature of proposed algorithm is its ability to calculate efficiency for multiple outputs. An example using real data is presented for illustrative purposes. In the application to the auto industries, we find that the neural network provide more robust results and identifies more efficient units than the conventional methods since better performance patterns are explored. To test the robustness of the efficiency results of the proposed method, the ability of proposed ANN algorithm in dealing with noisy and corrupted data is compared with Data Envelopment Analysis (DEA). Results of the robustness check show that the proposed algorithm is much more robust to the noise and corruption in input data than DEA.

No abstract