Evaluation and Prediction of the Efficiency of Industrial Companies Using a Hybrid Model of Data Envelopment Analysis and Artificial Neural Networks

Subject Areas : Industrial Management

Shahnaz Mohammadi Majd ^{1 *}

1 - Department of Mathematics and Statistics, Sanandaj Branch, Islamic Azad University, Sanandaj, Iran.

Received: 2025-02-01 Accepted : 2025-04-20 Published : 2025-02-17

Keywords: Artificial Neural Network, Data Envelopment Analysis, Efficiency Evaluation, Hybrid Model, Performance Prediction, .,

Abstract :

This paper presents a hybrid model based on Data Envelopment Analysis (DEA) and Artificial Neural Networks (ANN) to evaluate and predict the efficiency of 50 industrial companies operating in various sectors. Initially, DEA was employed to calculate the relative efficiency and identify efficient and inefficient decision-making units. Subsequently, the results obtained from DEA were used as target data to train the Artificial Neural Network (ANN). The ANN model, by uncovering hidden patterns in the data, was able to predict the future performance of companies with high accuracy. The results demonstrate that the DEA-ANN hybrid model not only provides a precise assessment of companies' current efficiency but also predicts efficiency changes in the event of input variations. Additionally, by utilizing the trained neural network, it is possible to predict the efficiency of companies that have not been directly evaluated. This approach, combining the strengths of DEA in efficiency analysis and the capabilities of ANN in modeling nonlinear relationships, offers an effective tool for managers and decision-makers to improve performance and optimize resource allocation.

References:

Bahrami, F., Abbasi, M., & Rahimi, S. (2022). Combining data envelopment analysis models and machine learning algorithms for evaluating the
efficiency of decision-making units considering undesirable outputs. Journal of Industrial Management and Systems, 14(4), 23–35. Fallah, H., Karimi, N., & Rezaei, A. (2023). A hybrid model of data envelopment analysis and artificial neural networks for evaluating the efficiency of pharmaceutical companies. Journal of Industrial Management Technology, 12(1), 45–59
. Sharifi, R., & Mohammadi, M. (2020). Applying a hybrid approach of data envelopment analysis and artificial neural networks in evaluating the performance of Iran Darou pharmaceutical company. Journal of Iranian Industrial Management Research, 10(2), 89–104
. Nadri, K., & Rostami, A. (2021). A model for improving comparative performance evaluation of companies using artificial neural networks and data envelopment analysis. In Proceedings of the National Conference on New Technologies in Management and Industrial Engineering, 15(3), 67–78
. Alavi, H. (2019). Efficiency prediction considering nonlinear impacts of time delays in data envelopment analysis. Journal of Iranian Industrial Management, 11(3), 45–58
. Banker, R. D., Charnes, A., & Cooper, W. W. (1984). Some models for estimating technical and scale inefficiencies in data envelopment analysis. Management Science, 30(9), 1078–1092
Charnes, A., Cooper, W. W., & Rhodes, E. (1978). Measuring the efficiency of decision-making units. European Journal of Operational Research, 2(6), 429–444.
Emrouznejad, A., & Yang, G. (2018). A survey and analysis of the first 40 years of scholarly literature in DEA: 1978–2016. Socio-Economic Planning Sciences, 61, 4–8
. Jin, Y., Li, Y., & Hu, J. (2016). Applying artificial neural networks to predict hospital efficiency in the context of health care reform. Health Care Management Science, 19(4), 302–314

Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536. Sadeghi, J., Sadeghi, S., & Ahmadi, A. (2015). Evaluating the efficiency of automotive companies using a hybrid DEA-ANN model. Journal of Industrial Engineering International, 11(3), 389–402
. Wang, T., Zhu, Q., & Chu, J. (2011). Using data envelopment analysis and neural networks for efficiency evaluation and prediction. Mathematical and Computer Modelling, 54(11–12), 2760–2771
Zhang, J., & Lin, C. (2020). Performance evaluation of industrial firms using DEA and DECORATE ensemble method. Expert Systems with Applications, 143, 113048
. Feng, L., & Wei, C. (2021). Developing and training artificial neural networks using bootstrap data envelopment analysis for best performance modeling of sawmills in Ontario. Journal of Modelling in Management, 16(3), 765–785
. Kao, C., & Liu, S. (2004). Predicting performance improvement using DEA and ANN. Computers & Operations Research, 31(10), 1875–1886
.