Journal of Industrial and Systems Engineering

Journal of Industrial and Systems Engineering

Reducing risk and increasing income of bank customers by Optimizing data mining for the multi-objective model of allocating facilities.

Document Type : Research Paper

Authors
Roya Cheshmi Khani 1
Mohammad Ali Afshar Kazemi 2
Abbas Toloie Eshlaghy 2
Ezzatollah Asgharizadeh 3
1 Ph.D. Student in Industrial Management, Department of Industrial Management, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 Full Professor, Department of Industrial Management, Science and Research Branch, Islamic Azad University, Tehran, Iran.
3 Department of Management and economics , Tehran University, Tehran, Iran.
Abstract
Iranian Commercial banks are always considered as one of the most important institutions active in the money and capital market, due to the economic structure of the country and the lack of development of the capital markets, which makes them in charge of financing the economic sectors of the country. However, these banks are not successful in fulfilling their mission. High level of banks' reserves shows that they do not pay enough attention to risk management and credit portfolio management. There are several models such as linear programming, integer programming, zero and one programming that can provide an optimal combination of the elements that make up the facility basket. However, entering financial information into mathematical planning by considering all conditions is not straightforward to achieve such a goal. In this research, using data mining to optimize the multi-objective model of facility allocation is done using neural network. First, the effective variables were extracted from the bank database and after preparation, the most important features were identified using different algorithms such as random forest algorithm, MARS, and step-wise regression. Then, these methods were compared with each other and the best method was selected. In order to cluster the customers, k-means and k-medoids models have been used. Using different criteria, including the silhouette and the best number of clusters, two clusters have been estimated and customers have been identified in two low-risk and high-risk categories. And finally, by using convolutional neural network, the risk and profit of each customer has been predicted.
Keywords
loan
data mining
clustering
deep learning
convolutional neural network
CNN
LSTM
Subjects
Adnan et al, R.M.,(2020). Least square support vector machine and multivariate adaptive regression splines for streamflow prediction in mountainous basin using hydro-meteorological data as inputs,J. Hydrol.156-159.
Al Machot,F. et al.(2019). A deep-learning model for subject-independent human emotion recognition using electrodermal activity sensors.219-231.
Ansari,A., Riasi،,A., (2016).  Customer Clustering Using a Combination of Fuzzy C-Means and Genetic Algorithms, 34-51.
Armantier, O., Ghysels, E., Sarkar, A., Shrader, J., (2015). Discount window stigma during the 2007-2008 financial crisis. J. Financ. Econ. 118 (2), 317–335.
Bernanke, B.,( 2009). The federal reserve's balance sheet: an update. In: A Speech at the Federal Reserve Board Conference on Key Developments in Monetary Policy, Washington, D.C.210-213.
Bhandari, P.,(2022). Missing Data | Types, Explanation, & Imputation. Revised on November 11, 2022.
Bock , H.,(2007). Clustering methods: A history of k-means algorithmsSelected Contributions in Data Analysis and Classification, . 161-172.
Bose, I., Chen, X.,(2015). Detecting the migration of mobile service customers using fuzzy clustering.
Chen, X.D. ,(2017). Analysis and research of common clustering algorithm in data miningDigital Technol. Appl.,  pp. 151-152.
De Andrés et al. J.,(2011). Bankruptcy forecasting: a hybrid approach using Fuzzy c-means clustering and Multivariate Adaptive Regression Splines (MARS). 45-51.
Dormann et al, C.F.,(2013). Collinearity: a review of methods to deal with it and a simulation study evaluating their performance.201-203.
Du S., Li J.,(2019). Parallel processing of improved knn text classification algorithm based on Hadoop. In: 2019 7th International Conference on Information, Communication and Networks (ICICN), 167-170.
Estivill-Castro V., Houle M.E.(2001). Robust distance-based clustering with applications to spatial data mining,Algorithmica, 30 (2) , 216-242.
Gharachorloo, N., Nahr, J. G., & Nozari, H. (2021). SWOT analysis in the General Organization of Labor, Cooperation and Social Welfare of East Azerbaijan Province with a scientific and technological approach. International Journal of Innovation in Engineering, 1(4), 47-61.
Guo,G.,  Wang, H.,  Bell, D.,  Greer, Y.,(2003). KNN model-based approach in classificationOTM Confederated International Conferences on the Move to Meaningful Internet Systems, 986-996.
Hajjem, A.,  Bellavance, F.,  Larocque, D.,(2014). Mixed-effects random forest for clustered dataJ. Stat. Comput. Simul, 1313-1328.
Henderi, T., Wahyuningsih,T. ,Rahwanto,E.,(2021). Comparison of Min-Max normalization and Z-Score Normalization in the K-nearest neighbor(KNN) Algorithm to Test the Accuracy  of Type so Breast Cance, International Journal of Informatics and Information SystemVol.4,NO.1,13-20.
Howell, E.,(2021). 4 Techniques To Deal With Missing Data in Datasets, Simple methods that can nullify the effects of missing values, Published in Towards Data Science, Sep 17.
Huang et al.,  Huang J., Wei Y., Yi J., Liu M.,(2018). An improved kNN based on class contribution and feature weighting. In: 2018 10th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), 313-316.
Huang, X.Y. ,(2018). An improved KNN algorithm and its application in real-time car-sharing predictionDalian University of Technology, Daian, China ,M.S. thesis.222-225.
Khosroyani, M., Heydarpoor, F., Yaghoob-nezhad, A., & Poorzamani,Z.(2022). An artificial neural network model for predicting the liquidity risk of Iranian private banks. Int. J. Nonlinear Anal. Appl. In Press, 1–11 ISSN: 2008-6822 (electronic); http://dx.doi.org/10.22075/ijnaa.2022.29118.4071. [In Persian].
Miller, A., (2002). Subset Selection in Regression, 2nd ed. Boca Raton, USA: Chapman and Hall, CRC Press.10.1201/9781420035933.
Mohammadi, N.,  Zangeneh, M.,(2016). Customer credit risk assessment using artificial neural networksIJ Information Technology and Computer Science, 8 (3) , 58-66.
Ngufor, C., Van Houten, H., Caffo, B.S., Shah, N.D., McCoy, R.G.,(2019). Mixed Effect Machine Learning: a framework for predicting longitudinal change in hemoglobin A1cJ. Biomed. Inform, 56-67
Nozari, H. (2024). Investigating Key Dimensions and Key Indicators of AIoT-Based Supply Chain in Sustainable Business Development. In Artificial Intelligence of Things for Achieving Sustainable Development Goals (pp. 293-310). Cham: Springer Nature Switzerland.
Nozari, H., Sadeghi, M. E., Eskandari, J., & Ghorbani, E. (2012). Using integrated fuzzy AHP and fuzzy TOPSIS methods to explore the impact of knowledge management tools in staff empowerment (Case study in knowledge-based companies located on science and technology parks in Iran). International journal of information, business and management, 4(2), 75-92.
Ole Hjelkrem,L.,  Eilif de Lange.P(2023). Explaining Deep Learning Models for Credit Scoring with SHAP: A Case Study Using Open Banking Data, J. Risk Financial Manag. 2023, 16(4), 221; https://doi.org/10.3390/jrfm16040221.
Ray,S., ( 2019). A quick review of machine learning algorithms. In: 2019 International conference on machine learning, big data, cloud and parallel computing (COMITCon), IEEE, 35-39.
Sabo, S., (2014). Analysis of the k-means algorithm in the case of data points occurring on the border of two or more clusters.
Speiser, J.L.,Wolf, B.J., Chung, D., Karvellas, C.J., Koch, D.G., Durkalski V.L.,(2019). BiMM forest: A random forest method for modeling clustered and longitudinal binary outcomesChemometrics Intell. Lab. Syst.
Tavakkoli-Moghaddam, R., Ghahremani-Nahr, J., Samadi Parviznejad, P., Nozari, H., & Najafi, E. (2022). Application of internet of things in the food supply chain: a literature review. Journal of applied research on industrial engineering, 9(4), 475-492.
Teles, G., Rodringues, J., Rabelo , R., & Kozlov, S.,(2020) Artificial neural network and Bayesian network models for credit risk prediction, J. Artif. Intel. Syst. no. 1, 118–132.
Wang, P.(2018). Research on Application of Big Data in Internet Financial Credit Investigation Based on Improved GA-BP Neural Network, Volume 2018, Article ID 7616537, https://doi.org/10.1155/2018/7616537.
Wang, Q., Wang, S., Wei, B., Chen, V., Zhang, Y.,(2021). Weighted K-NN classification method of bearings fault diagnosis with multi-dimensional sensitive featuresIEEE Access, 45428-45440, 10.1109/ACCESS.2021.3066489.
Wang,h.,Xu,P.,Zhao , J.,(2022). Improved KNN algorithms of spherical regions based on clustering and region division, Alexandria Engineering Journal,Volume 61, Issue 5,  3571-3585.
Yanenkova ,I .Nehoda,Y. Drobyazko,S. Zavhorodnii, A. Beresovska,L(2021). Modeling of Bank Credit Risk Management Using the Cost Risk Model, Risk Financial Manag. , 14(5), 211; https://doi.org/10.3390/jrfm14050211
Yang, Z., Xiaolong ,Su،.,(2012). Customer Behavior Clustering Using SVM.
Zach,A.,(2021). Z-Score Normalization: Definition & Examples, https://www.statology.org/z-score-normalization/
Zhang, Q., Couloigner ,I.,(2005). A new and efficient K-medoid algorithm for spatial clustering. In: Lecture notes in computer science, vol. 3482, (III), http://dx.doi.org/10.1007/11424857_20.
Zhang,Z.,(2016),Introduction to machine learning: k-nearest neighbors,Ann. Transl. Med., 4 (11) .
Zhou, S.,  Bao, Y. Lu, D., Wang, K.,  Shan, J., Hou, Z., (2022). Real-time data-driven fault diagnosis of proton exchange membrane fuel cell system based on binary encoding convolutional neural network,Int J Hydrogen Energy, 47 (20) , 10976-10989.

  • Receive Date 19 November 2023
  • Revise Date 26 December 2023
  • Accept Date 30 December 2023