نوع مقاله : مقاله پژوهشی - کاربردی

نویسندگان

1 گروه مدیریت صنعتی، دانشکده اقتصاد و مدیریت، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.

2 گروه مدیریت صنعتی، دانشکده اقتصاد و مدیریت، واحد تهران مرکز، دانشگاه آزاد اسلامی، تهران، ایران.

10.22105/dmor.2021.246994.1211

چکیده

هدف از این تحقیق، تلفیق دو روش تحلیل پوششی داده ها و شبکه عصبی بمنظور ارائه یک مدل بهینه برای رتبه‌بندی عوامل ناکارایی در صنعت بانکداری ایران است. ابتدا از طریق مطالعه مبانی نظری و مصاحبه با خبرگان بانکی شاخص‌های ارزیابی کارایی در صنعت بانکداری شناسایی و نهایی گردید. در ادامه بمنظور ارزیابی کارایی واحدها در جامعه آماری مورد مطالعه از تکنیک تحلیل پوششی داده ها به ویژه مدل برنامه ریزی آرمانی اصلاح شده تحلیل پوششی داده ها استفاده شد، که از 32 مدیریت بانک مورد مطالعه، 3 مدیریت کارا و 29 مدیریت ناکارا تشخیص داده شدند. سپس شعب زیر مجموعه مدیریت های ناکارا مورد ارزیابی قرار گرفته و با استفاده از اطلاعات شعب ناکارا ماتریس شبکه‌ عصبی برای تشخیص عوامل ناکارایی تهیه و با مدل های مختلف شبکه عصبی به تحلیل نتایج پرداخته شد. مدلی که کمترین میانگین مجذور خطا را داشته باشد به عنوان مدل بهینه به منظور تعیین عوامل ناکارایی انتخاب خواهد شد، در نتیجه مدل نگاشت خود سازمانده با تابع انتقال تانژانت هیپربولیک و با قاعده آموزش ممنتم 0/9 انتخاب گردید. با تحلیل حساسیت روش مذکور شاخص‌های سهم نقدینگی استانها، توزیع پرسنل و هزینه های عملیاتی به عنوان مهمترین عوامل ناکارایی انتخاب شدند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Provide an optimal model for determining and ranking inefficiency factors in the banking industry by combining data envelopment analysis and neural network

نویسندگان [English]

  • Gholamreza Panahandeh Khojin 1
  • Abbas Toloie Ashlaghi 1
  • Mohamad Ali Afshar Kazmi 2

1 Department of Industrial Management, Faculty of Economics and Management, Science and Research Branch, Islamic Azad University, Tehran, Iran.

2 Department of Industrial Management, Faculty of Economics and Management, Central Tehran Branch, Islamic Azad University, Tehran, Iran.

چکیده [English]

The purpose of this study is to combine two methods of data envelopment analysis and neural network in order to provide an optimal model for ranking inefficiency factors in the Iranian banking industry. First, through the study of theoretical foundations and interviews with banking experts, efficiency evaluation indicators in the banking industry were identified and finalized. In order to evaluate the efficiency of the units in the statistical population of the study, data envelopment analysis technique was used, especially the modified goal programming data envelopment analysis model, which was identified from 32 managements, 3 efficient managements and 29 inefficient managements. Then, the branches of inefficient management were evaluated and using the information of inefficient branches, the neural network matrix was prepared to identify the causes of inefficiency and the results were analyzed with different neural network models. The model with the lowest mean square error will be selected as the optimal model to determine the inefficiency factors. As a result, the self-organized mapping model with hyperbolic tangent transfer function and 0.9 momentum training rule was selected. By analyzing the sensitivity of this method, the indicators of provincial liquidity share, personnel distribution and operating costs were selected as the most important factors of inefficiency.

کلیدواژه‌ها [English]

  • Data envelopment analysis
  • Modified goal programming data envelopment analysis
  • Neural network
  • Self-organized neural network
  • Inefficiency factors
Ahadzadeh Namin, M., Khamseh, E., & Mohamadi, F. (2019). Evaluate the performance of bank branches using the control approach in analyzing the data common weight. Financial engineering and securities management, 10(40), 1-28. (In Persian). https://civilica.com/doc/958478
Aliheidari Bioki, T., & Khademi Zare, H. (2014). Adaptive DEA for clustering of credit clients. Journal of applied research on industrial engineering1(1), 35-49. http://www.journal-aprie.com/article_43017.html
Arabmazar, A., Varahrami, V., & Hasani, H. (2018). Survey performance of Iran’s banks with network data envelopment analysis method. Quarterly journal of quantitative economics, 15(2), 1-21. (In Persian). DOI: 10.22055/jqe.2017.21388.1596
Ardabili Miyanaj, P., & Borimnezhad, V. (2017). Evaluation of agricultural bank branches performance using data envelopment analysis: case study of alborz province. Journal of agriclutural economices research, 8(32), 19-38. (In Persian). 20.1001.1.20086407.1395.8.32.2.8
Azizi, J. (2015). Evaluation of the efficiency of the agricultural bank branches by using data envelopment analysis and the determination of a consolidated index: the case study in mazandaran province. Agricultural economics, 9(1), 63-76. (In Persian). http://ensani.ir/file/download/article/20150706141047-9437-202.pdf
Bal, H., Örkcü, H. H., & Çelebioğlu, S. (2010). Improving the discrimination power and weights dispersion in the data envelopment analysis. Computers & operations research37(1), 99-107. https://doi.org/10.1016/j.cor.2009.03.028
Charnes, A., Cooper, W. W., & Rhodes, E. (1978). Measuring the efficiency of decision making units. European journal of operational research2(6), 429-444. https://doi.org/10.1016/0377-2217(78)90138-8
Dadmohammadi, D., & Ahmadi, A. (2014). Credit rating of bank customers using neural network with lateral connections. Monetary and banking management development quarterly, 2(3), 1-28. (In Persian). https://journal.ansarbank.ir/article_9005.html
Daneshvar, S., Shahi, N., & Najafzadeh, F. (2015). Modified goal programming approach for improving the discrimination power and weights dispersion. Journal of new researches in mathematics, 1(3), 5-18. https://www.sid.ir/paper/257260/en
Elahi, Sh., Ghods Elahi, A., & Naji, H. R. (2014). Presenting a hybrid model of neural networks using collective learning in order to assess credit risk. Iran information and communication technology quarterly, 20(6). (In Persian). http://jour.aicti.ir/Article/6581/FullText
Faghih, H. (2010). Evaluating artificial neural network and its optimization using genetic algorithm in estimation of monthly precipitation data (case study: Kurdistan region). JWSS, 14(51), 27-42. (In Persian). https://www.sid.ir/paper/14867/fa
Farrell, M. J. (1957). The measurement of productive efficiency. Journal of the royal statistical society: series A(general)120(3), 253-281.
Ghasem Nia Arabi, N., & Safaei Ghadi Kolaei, A. (2018). Comparing the performance of classical models and artificial intelligence in predicting the credit status of bank customers. Scientific-research journal of business management explorations, 10(20), 51-69. (In Persian). https://sid.ir/fileserver/jf/4003313972003
Heidary, S., Zanburi, E., & Parvin, H. (2018). A hybrid model based on neural network and data envelopment analysis model for evaluation of unit performance. Iranian journal of optimization, 10(2), 101-112. (In Persian). https://journals.iau.ir/article_537750_7a9f12b441f6b39322346234381df15e.pdf
Hosseinzadeh Lotfi, F., & Jahanbakhsh, M. (2015). Assess the efficiency and effectiveness simultaneously in a three-stage process, by using a unified model. International journal of research in industrial engineering4(1(4)), 15-23. https://doi.org/10.22105/riej.2017.49165
Jaberi, M., Najafi, S. E., Hoseinzadeh Lotfi, F., & Haji Molana, M. (2021). A comprehensive hybrid NDEA-Bsc model and a new neural network for predicting organizational performance indicators. Journal of decisions and operations research6(2), 271-287. (In Persian). DOI: 10.22105/dmor.2020.254632.1243
Jahangiri, A. (2019). Application of data envelopment analysis technique in Iran banking system. Journal of decisions and operations research, 3(4), 368-401. (In Persian). https://doi.org/10.22105/dmor.2019.82229
Katsoufi, S., Lazou, A. E., Giannakourou, M. C., & Krokida, M. K. (2017). Mass transfer kinetics and quality attributes of osmo-dehydrated candied pumpkins using nutritious sweeteners. Journal of food science and technology54(10), 3338-3348. https://doi.org/10.1007/s13197-017-2786-2
Li, X. B., & Reeves, G. R. (1999). A multiple criteria approach to data envelopment analysis. European journal of operational research115(3), 507-517. https://doi.org/10.1016/S0377-2217(98)00130-1
Mehrabian, S., Saati-Mohtadi, S., & Hadi, A. (2011). Evaluating the efficiency of New Economy Bank branches with a combination of neural network method and data envelopment analysis. Operations research in its applications, 8(4). (In Persian). https://jamlu.liau.ac.ir/article-1-329-fa.html
Mehrara, M., & Mehran Far, M. (2015). Bank and macroeconomic variables efficiency in risk management. Economic modeling7(21), 21-37. (In Persian). https://eco.firuzkuh.iau.ir/article_555431_en.html?lang=fa
Minhaj, M. B. (2005). Basics of neural networks. Amir Kabir University, Tehran. (In Persian). http://publication.aut.ac.ir/fa/book/show/711
Mir Ghafouri, S. H., Morovatti Sharifabadi, A., & Zamani, F. (2014). Providing an integrated model of data envelopment analysis and artificial neural networks to evaluate and predict the performance of case study bank branches (Tejarat Bank Yazd branches). The third national accounting and management conference, Tehran, Iran. Civilica. (In Persian). https://civilica.com/doc/342996/
Moghaddas, Z., & Vaez Ghasemi, M. (2021). Cost efficiency evaluation for a two-stage series network in data envelopment analysis. Innovation management and operational strategies, 1(1), 48-56. (In Persian). DOI: 10.22105/imos.2021.262727.1018
Nilchi, M., Fadaeinejad, M., Razavi-Hajiagha, S., & Badri, A. (2017). Providing new multi-component data envelopment analysis to evaluate efficiency of bank branches. Industrial management studies, 15(46), 73-96. (In Persian).  DOI: 10.22054/jims.2017.7989
Rajabzadeh Ghatari, A., Mirzaei, A. B., & Ahmadi, P. (2009).  Designing a combined intelligent system for credit rating of bank customers using combined fuzzy reasoning models. Quarterly journal of business research, 53, 159-201. (In Persian). https://sid.ir/fileserver/jf/51213885306
Ranjbar, M., BakyHaskouei, M., & Farahanifard, S. (2016). The study of effective factors on Iranian banking system technical performance by applying panel data approach. Journal of econometric modeling, 1(3), 23-42. (In Persian). DOI:  10.22075/JEM.2017.1509
Sabonian, M., & Behnajady, M. A. (2018). Application of artificial neural networks in the modeling of photocatalytic reduction of Cr (VI) by titanium dioxide nanoparticles: optimization of artificial neural network structure. Iranian journal of health and environment11(2), 183-196. (In Persian). http://ijhe.tums.ac.ir/article-1-5979-fa.html
Sadorsky, P. (2006). Modeling and forecasting petroleum futures volatility. Energy economics28(4), 467-488. https://doi.org/10.1016/j.eneco.2006.04.005
Sahoo, B. K., Mehdiloozad, M., & Tone, K. (2014). Cost, revenue and profit efficiency measurement in DEA: a directional distance function approach. European journal of operational research237(3), 921-931. https://doi.org/10.1016/j.ejor.2014.02.017
Wesolowski, M., & Suchacz, B. (2012). Artificial neural networks: theoretical background and pharmaceutical applications: a review. Journal of AOAC international95(3), 652-668. https://doi.org/10.5740/jaoacint.SGE_Wesolowski_ANN