Bulanık Çok Kriterli Karar Verme ve Kendi Kendini Düzenleyen Haritalar Kullanarak Şirketlerin Finansal Değerlendirmesine Yönelik Hibrit Yaklaşım

Year 2024, Volume: 13 Issue: 2, 610 - 629, 01.07.2024

Fatih Yiğit

https://doi.org/10.15869/itobiad.1404060

Abstract

Bu makale, finansal oranları Bulanık Analitik Hiyerarşi Süreci (FAHP) ile entegre eden ve sınıflandırma için denetimsiz yapay zeka yöntemi olan Kendi Kendini Düzenleyen Haritaları (SOM) kullanan şirketlerin finansal performanslarının değerlendirilmesi için 3 aşamalı yenilikçi bir yaklaşım sunmaktadır. Kaynak tahsisinde karar vermenin zorluklarını ele alan çalışma, doğru verileri çalkantılı ekonomik dönemlerde gerekli olan sağlam araçlarla birleştirmektedir. Karmaşık ve belirsiz bilgileri işlemesiyle bilinen FAHP, farklı uzmanların görüşlerini entegre ederek ve sayısal değerlere dönüştürerek geleneksel şirket değerlendirme yöntemlerini geliştirmek için uygulanır. Bu çalışma, karmaşık ve belirsiz verileri işleyebilen FAHP ile bütünleştirerek yenilikçi bir çerçeve sunmaktadır. Finansal oranların FAHP'ye entegrasyonu, şirketlerin değerlendirilmesi ve sıralanmasında doğruluğu ve karar verme süreçlerindeki netliği artırırken, ekonomik verilerin doğasındaki belirsizliklerin yönetilmesine olanak tanır. Ek olarak, şirket sınıflandırması için denetimsiz yapay zeka yöntemi olan SOM kullanımı, metodolojimizin etkinliğini gerçek hayat verileri üzerinden ispatlamaktadır. Çalışmanın sonuçlarına göre, Net Kâr Marjı, finansal oranlar arasında 0.38 ile en yüksek ağırlığa sahip olarak değerlendirilen finansal orandır. FAHP aşamasından sonra, firmaların gelir tablosu ve bilançolarından elde edilen finansal oranlar söz konusu ağıırlıklarla çarpılarak değerleme gerçekleştirilmektedir. Son aşamada ise Borsa Istanbul- Sigorta Endeksinde işlem gören toplam 6 şirket 3 sınıfa göre ayrılmıştır. En yüksek değerlemeyi alan 2 firma, AGESA(Agesa Hayat ve Emeklilik) ile ANHYT (Anadolu Hayat Emeklilik Anonim Şirketi), A sınıfı olarak değerlendirilmiştir. Önerilen makalenin performansının tespiti için Elektrik sektöründe XELKT kayıtlı 31 firma ile de uygulama yapılmıştır. Makale, ayrıntılı bir literatür taraması, metodoloji, vaka çalışması sonuçları ve bu entegre değerlendirme yönteminin pratik uygulamaları ve daha ileri araştırma ve uygulamalar için olası alanlar hakkında tartışmalar sağlayarak alana katkıda bulunmaktadır.

Keywords

Finansal Değerlendirme, Çok Kriterli Karar Verme, Bulanık Analitik Hierarşi Prosesi, Makine Öğrenmesi, Kendi-Kendini Düzenleyen Haritalar

Hybrid Approach for the Financial Assessment of Companies using Fuzzy Multi-Criteria Decision-Making and Self-Organizing Maps

Abstract

This paper presents a 3-stage innovative approach for company assessment, integrating financial ratios with the Fuzzy Analytic Hierarchy Process (FAHP) and using an unsupervised artificial intelligence method, Self-Organizing Maps (SOM), for classification. Addressing the challenges of decision-making in resource allocation, the study combines accurate data with robust tools essential in turbulent economic times. FAHP, known for handling complex, uncertain information, is applied to refine the traditional company assessment methods by integrating different experts' opinions and conversion to numerical values. This study presents an innovative framework by integrating financial ratios, commonly used in company evaluation methodologies, with FAHP, which is capable of processing complex and uncertain data. The integration of financial ratios into FAHP enhances the accuracy and clarity in decision-making processes for evaluating and ranking companies while also allowing for the management of the inherent uncertainties in economic data. Furthermore, SOM, an unsupervised artificial intelligence method for company classification, is used. Net Profit Margin is the financial ratio evaluated with the highest weight among financial ratios by 0.38. After the FAHP phase, financial ratios obtained from the income statements and balance sheets of companies are multiplied by the respective weights for valuation. In the final phase, a total of 6 companies listed in the Borsa Istanbul Insurance Index are divided into 3 classes. The two companies receiving the highest valuation, AGESA (Agesa Life and Pension) and ANHYT (Anadolu Life Pension Joint Stock Company), have been classified as Class A. To show the performance of the proposed model, companies registered in the Electricity Sector XELKT registered 31 companies. Classification also performed well in that set. The paper contributes to the field by providing a detailed literature review, methodology, case study results, and discussions on the practical implications of this integrated assessment method and possible areas for further research and applications.

Keywords

Financial Analysis, Multi-Criteria Decision Making, Fuzzy Analytic Hierarchy Process, Machine Learning, Self-Organizing Maps

References

• Abusaeed, S., Khan, S. U. R., & Mashkoor, A. (2023). A Fuzzy AHP-based approach for prioritization of cost overhead factors in agile software development. Applied Soft Computing, 133, 109977. https://doi.org/10.1016/j.asoc.2022.109977
• Adenso-Díaz, B., Álvarez, N. G., & Alba, J. A. L. (2020). A fuzzy AHP classification of container terminals. Maritime Economics and Logistics, 22(2), 218–238. https://doi.org/10.1057/s41278-019-00144-4
• Aldalou, E., & Perçin, S. (2018). Financial Performance Evaluation of Turkish Airline Companies Using Integrated Fuzzy Ahp Fuzzy Topsis Model*. Uluslararası İktisadi ve İdari İncelemeler Dergisi. https://doi.org/10.18092/ulikidince.347925
• Basílio, M. P., Pereira, V., Costa, H. G., Santos, M., & Ghosh, A. (2022). A Systematic Review of the Applications of Multi-Criteria Decision Aid Methods (1977–2022). In Electronics (Switzerland) (Vol. 11, Issue 11). MDPI. https://doi.org/10.3390/electronics11111720
• Başaran, Y., Aladağ, H., & Işık, Z. (2023). Pythagorean Fuzzy AHP Based Dynamic Subcontractor Management Framework. Buildings, 13(5), 1351. https://doi.org/10.3390/buildings13051351 Beaver, W. (1966). Financial Ratios As Predictors Of Failure. https://doi.org/10.2307/2490171
• Buckley, J. J. (1985). Fuzzy hierarchical analysis. Fuzzy Sets and Systems, 17(3), 233–247.
• Burova, A., Penikas, H., & Popova, S. (2021). Probability of Default Model to Estimate Ex Ante Credit Risk. Russian Journal of Money and Finance. https://doi.org/10.31477/RJMF.202103.49
• Çolakoğlu, N., & Şahi̇n, Z. (2022). Determining of Priorities in ERP Project Management with AHP Approach. Eurasian Academy of SciencesEurasian Business & Economics Journal 30, 39-63
• Demircan, B. G., & Yetilmezsoy, K. (2023). A Hybrid Fuzzy AHP-TOPSIS Approach for Implementation of Smart Sustainable Waste Management Strategies. Sustainability, 15(8), 6526. https://doi.org/10.3390/su15086526
• Duyck, C., da Silva Viana Jacobson, L., Rodrigues de Souza, J., Chavez Rocha, R. C., Oliveira, C. J. F., Oliveira da Fonseca, T. C., & Saint’Pierre, T. D. (2023). Brazilian basins characterization based on the distributions of elements in desalted crude oils using classical multivariate analysis and kohonen self-organizing map. Geoenergy Science and Engineering, 223. https://doi.org/10.1016/j.geoen.2023.211502
• Ertuǧrul, I., & Karakaşoǧlu, N. (2009). Performance evaluation of Turkish cement firms with fuzzy analytic hierarchy process and TOPSIS methods. Expert Systems with Applications, 36(1), 702–715. https://doi.org/10.1016/j.eswa.2007.10.014
• Ishizaka, A., & Mu, E. (2023). What is so special about the analytic hierarchy and network process? In Annals of Operations Research (Vol. 326, Issue 2, pp. 625–634). Springer. https://doi.org/10.1007/s10479-023-05412-4
• Kahraman, C. (2024). Proportional picture fuzzy sets and their AHP extension: Application to waste disposal site selection. Expert Systems with Applications, 238, 122354. https://doi.org/10.1016/j.eswa.2023.122354
• Khan, A. U., Khan, A. U., & Ali, Y. (2020). ANALYTICAL HIERARCHY PROCESS (AHP) AND ANALYTIC NETWORK PROCESS METHODS AND THEIR APPLICATIONS: A TWENTY YEAR REVIEW FROM 2000–2019. International Journal of the Analytic Hierarchy Process, 12(3), 369–402. https://doi.org/10.13033/IJAHP.V12I3.822
• Kohonen, T. (2013). Essentials of the self-organizing map. Neural Networks, 37, 52–65. https://doi.org/https://doi.org/10.1016/j.neunet.2012.09.018
• Kubler, S., Robert, J., Derigent, W., Voisin, A., & Le Traon, Y. (2016). A state-of the-art survey & testbed of fuzzy AHP (FAHP) applications. Expert Systems with Applications, 65, 398–422. https://doi.org/10.1016/j.eswa.2016.08.064
• Labib, A., Abdi, M. R., Hadleigh-Dunn, S., & Yazdani, M. (2022). Evidence-Based Models To Support Humanitarian Operatıons And Crisis Management. Decision Making: Applications in Management and Engineering, 5(1), 113–134. https://doi.org/10.31181/dmame030222100y
• Liu, Y., Eckert, C. M., & Earl, C. (2020). A review of fuzzy AHP methods for decision-making with subjective judgements. Expert Systems with Applications, 161, 113738. https://doi.org/10.1016/j.eswa.2020.113738
• Madzík, P., & Falát, L. (2022). State-of-the-art on analytic hierarchy process in the last 40 years: Literature review based on Latent Dirichlet Allocation topic modelling. In PLoS ONE (Vol. 17, Issue 5 May). Public Library of Science. https://doi.org/10.1371/journal.pone.0268777
• McGuigan, J. R., Kretlow, W. J., Moyer, R. C., & Wang, B. (2006). Contemporary financial management. Thomson/South-Western.
• Moghimi, R., & Anvari, A. (2014). An integrated fuzzy MCDM approach and analysis to evaluate the financial performance of Iranian cement companies. The International Journal of Advanced Manufacturing Technology, 71(1–4), 685–698. https://doi.org/10.1007/s00170-013-5370-6
• Nagy, M., & Valaskova, K. (2023). An Analysis of the Financial Health of Companies Concerning the Business Environment of the V4 Countries. Folia Oeconomica Stetinensia. https://doi.org/10.2478/FOLI-2023-0009
• Ozturk, H., & Karabulut, T. A. (2020). Impact of financial ratios on technology and telecommunication stock returns: Evidence from an emerging market. Investment Management and Financial Innovations, 17(2), 76–87. https://doi.org/10.21511/imfi.17(2).2020.07
• Rankovic, N., Rankovic, D., Lukic, I., Savic, N., & Jovanovic, V. (2023). Unveiling the Comorbidities of Chronic Diseases in Serbia Using ML Algorithms and Kohonen Self-Organizing Maps for Personalized Healthcare Frameworks. Journal of Personalized Medicine, 13(7). https://doi.org/10.3390/jpm13071032
• Saaty, T. (1980). The analytic hierarchy process (AHP) for decision making. Kobe, Japan, 1–69.
• Seçme, N. Y., Bayrakdaroğlu, A., & Kahraman, C. (2009). Fuzzy performance evaluation in Turkish Banking Sector using Analytic Hierarchy Process and TOPSIS. Expert Systems with Applications, 36(9), 11699–11709. https://doi.org/10.1016/j.eswa.2009.03.013
• Singh, S., & Garg, H. (2017). Distance measures between type-2 intuitionistic fuzzy sets and their application to multi-criteria decision-making process. Applied Intelligence. https://doi.org/10.1007/S10489-016-0869-9
• Syriopoulos, T., Tsatsaronis, M., & Gorila, M. (2020). The global cruise industry: Financial performance evaluation. Research in Transportation Business and Management, September, 100558. https://doi.org/10.1016/j.rtbm.2020.100558
• Tavana, M., Soltanifar, M., & Santos-Arteaga, F. J. (2021). Analytical hierarchy process: revolution and evolution. Annals of Operations Research. https://doi.org/10.1007/s10479-021-04432-2
• Tzeng, G.-H., & Huang, J.-J. (2011). Multiple attribute decision making: methods and applications. CRC press.
• Vibhakar, N. N., Tripathi, K. K., Johari, S., & Jha, K. N. (2023). Identification of significant financial performance indicators for the Indian construction companies. International Journal of Construction Management, 23(1), 13–23. https://doi.org/10.1080/15623599.2020.1844856
• Voda, A. D., Dobrotă, G., Țîrcă, D. M., Dumitrașcu, D. D., & Dobrotă, D. (2021). Corporate bankruptcy and insolvency prediction model. Technological and Economic Development of Economy, 27(5), 1039–1056. https://doi.org/10.3846/tede.2021.15106
• Yiğit, F. (2023). Classification of XTEKS Companies During COVID-19 Pandemic using Fuzzy-Analytic Hierarchy Process and Fuzzy-C-Means. In I. U. and O. B. and C. S. and C. O. S. and T. A. Ç. Kahraman Cengiz and Sari (Ed.), Intelligent and Fuzzy Systems (pp. 609–616). Springer Nature Switzerland.
• Yigit, P. (2023). Self-Organizing Maps Approach for Clustering OECD Countries Using Sustainable Development Indicators. İnsan ve Toplum Bilimleri Araştırmaları Dergisi, 12(5), 2850–2869. https://doi.org/10.15869/itobiad.1370419
• Yu, D., Huang, D., & Chen, L. (2023). Stock return predictability and cyclical movements in valuation ratios. Journal of Empirical Finance, 72, 36–53. https://doi.org/10.1016/j.jempfin.2023.02.004
• Zhang, X., Du, H., Zhao, Z., Wu, Y., Cao, Z., Zhou, Y., & Sun, Y. (2023). Risk Assessment Model System for Aquatic Animal Introduction Based on Analytic Hierarchy Process (AHP). Animals, 13(12). https://doi.org/10.3390/ani13122035