Ranking the determinants of financial performance using machine learning methods: an application to BIST energy companies

Year 2024, , 165 - 186, 31.12.2024

Hasan Hüseyin Yıldırım , Ömer Faruk Rençber , Cevriye Yüksel Yıldırım

https://doi.org/10.53391/mmnsa.1594426

Abstract

Energy has been a key driver of change globally. As a developing country, Türkiye's increasing energy demand and consumption highlight the growing importance of efficient and sustainable energy management for its future. This study aims to determine the variables of the financial performance of 12 energy companies. Three different models are created with the return on assets, return on equity, and net profit margin as financial performance indicators of 12 firms. 12 financial ratios are used as input variables as determinants of financial performance. In the analysis, 37 quarterly data between 2014Q4-2023Q4 are used as the sample period. In machine learning, 17 different algorithms are considered in the selection of the appropriate model. The findings indicate that the Bagged Tree algorithm achieved successful outcomes for the ROA target variable, the Boosted Tree model demonstrated effective performance for the ROE model, and the Linear SVM algorithm yielded favorable results for the NPM model. According to the result obtained by the LIME method, Liquidity Ratio and Cash Ratio affect the ROA, ROE, and NPM models positively, while inventory turnover affects the models negatively.

Keywords

Machine learning, financial performance, BIST, energy firms

References

• [1] Apan, M. and Islamoğlu, M. Determining the impact of financial characteristics on firm ˙ profitability: An empirical analysis on Borsa Istanbul energy firms. WSEAS Transactions on Business and Economics, 15, 547-559, (2018).
• [2] Iskenderoğlu, Ö., Karadeniz, E. and Ayyıldız, N. Enerji sektörünün finansal analizi: Türkiye ve Avrupa enerji sektörü karşılaştırması. Işletme ve Iktisat Çalışmaları Dergisi, 3(3), 86-97, (2015).
• [3] Yazgan, K.F. and Sakarya,Ş. (2023). Financial Analysis of the Energy Sector. In: Kılıç, Y., Buğan, M.F. and Bayrakdaroğlu, A. (eds.), Financial Analysis Applications in Borsa Istanbul: Sector-Based Reviews I. Özgür Publications.
• [4] Sakarya, S. and Yildirim, H. Determining the relation between financial performance and stock returns of energy companies on Borsa Istanbul with panel data analysis. Journal of Economics Finance and Accounting, 3(1), 71-88, (2016).
• [5] Yapraklı, S. Enerjiye Dayalı Büyüme: Türk Sanayi Sektörü Üzerine Uygulamalar. Beta Yayınevi: ˙ Istanbul, (2013).
• [6] Aydın, L. Enerji Ekonomisi ve Politikaları. Seçkin Yayıncılık: Ankara, (2014).
• [7] Koç, E. and Şenel, M.C. Dünyada ve Türkiye’de enerji durumu-genel değerlendirme. Mühendis ve Makina, 54(639), 32-44, (2013).
• [8] Silva, L. The problems with using renewable energy certificates to meet federal renewable energy requirements. Public Contract Law Journal, 41(4), 985–1006, (2011).
• [9] Anani, N., Al-Kharji AlAli, O., Al-Qutayri, M. and Al-Araji, S. Synchronization of a renewable energy inverter with the grid. Journal of Renewable and Sustainable Energy, 4(4), 043103, (2012).
• [10] Yıldırım, H.H. Financing methods of renewable energy projects in Turkey. Balıkesir University The Journal of Social Sciences Institute, 19(36-1), 725-746, (2016).
• [11] Ülkü, H. and Yalpır, Ş. Enerji talep tahmini için metodoloji geliştirme: 2030 yılı Türkiye örneği. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 10(1), 188-201, (2021).
• [12] Shin, H., Ellinger, A.E., Nolan, H.H., DeCoster, T.D. and Lane, F. An assessment of the association between renewable energy utilization and firm financial performance. Journal of Business Ethics, 151, 1121-1138, (2018).
• [13] ETKB, Enerji Verimliliği 2030 Stratejisi ve II. Ulusal Enerji Verimliliği Eylem Planı (2024-2030), (2024). https://enerji.gov.tr/Media/Dizin/BHIM/tr/Duyurular/T%C3% BCrkiyeninEnerjiVerimlili%C4%9Fi2030StratejisiveIIUlusalEnerjiVerimlili%C4% 9FiEylemPlan%C4%B1_202401161407.pdf
• [14] United Nations - Paris Agreement, (2015). https://unfccc.int/sites/default/files/ english_paris_agreement.pdf
• [15] Yazgan, K.F. and Saldanlı, A. Türkiye’de yenilenebilir enerji sektöründe devlet teşviklerinin rolü ve etkisi. In Finans; Teori ve Yaklaşımlar (pp. 1-29). Istanbul: Filiz Kitabevi, (2023).
• [16] IEA, World Energy Outlook, (2024). https://iea.blob.core.windows.net/assets/ 02b65de2-1939-47ee-8e8a-4f62c38c44b0/WorldEnergyOutlook2024.pdf
• [17] ETKB, 2023 Yılı Ulusal Enerji Denge Tablosu, (2023). https://enerji.gov.tr/ eigm-raporlari
• [18] Enerdata, Global Energy Transition Statistics, (2024). https://yearbook.enerdata.net/
• [19] ETKB, Türkiye Ulusal Enerji Planı, (2022). https://enerji.gov.tr/Media/Dizin/EIGM/tr/ Raporlar/TUEP/T%C3%BCrkiye_Ulusal_Enerji_Plan%C4%B1.pdf
• [20] Akusta, A. Comparative evaluation of statistical models and machine learning approaches in modelling the energy dependency of the BIST Industrial Index: Balancing predictive performance and interpretability. Journal of Corporate Governance, Insurance, and Risk Management, 11(3), 160-167, (2024a).
• [21] Yildirim, H.H. and Yavuz, M. Evaluation of wind energy investment with artificial neural networks. An International Journal of Optimization and Control: Theories & Applications (IJOCTA), 9(2), 142-147, (2019).
• [22] Doğan, M. and Erdoğan, B. Enerji firmalarının sermaye yapısına etki eden faktörler. Işletme ˙ Araştırmaları Dergisi, 16(3), 1974-1981, (2024).
• [23] Karabulut, T. BIST kurumsal yönetim endeksinde yer alan enerji firmalarının finansal performans göstergelerinin değerlendirilmesi. In Finansal Piyasaların Evrimi III (pp.93-106). Gaziantep: Özgür Yayınları, (2023).
• [24] KPMG, Enerji Sektör Raporu, (2024). https://assets.kpmg.com/content/dam/kpmg/tr/ pdf/2024/10/KPMG%20APlus%20Enerji%20Sekt%C3%B6r%20Raporu.pdf
• [25] Fintables, https://fintables.com/ [Access Date: 05.11.2024]
• [26] Finnet, https://finnet.com.tr/FinnetStore/Tr/ [Access Date: 05.11.2024]
• [27] KAP, Kamu Aydınlatma Platformu, https://www.kap.org.tr/tr/ [Access Date: 05.11.2024]
• [28] Kadıoğlu, S. and Sensoy, N. Enerji sektöründe yapılan finansal performans analizinde stok bulundurmanın etkisi. Istanbul Ticaret Üniversitesi Sosyal Bilimler Dergisi, 23(49), 1530-1543, (2024).
• [29] Uygurtürk, H. and Korkmaz, T. Finansal performansın TOPSIS çok kriterli karar verme yöntemi ile belirlenmesi: Ana metal sanayi işletmeleri üzerine bir uygulama. Eskişehir Osmangazi Üniversitesi I˙IBF Dergisi, ˙ 7(2), 95-115, (2012).
• [30] Aydın, N., Başar, M. and Çoşkun, M. Finansal Yönetim. Detay Yayıncılık: Ankara, (2021).
• [31] Dikmen, B.B. Elektrik enerjisi sektörünün finansal performanslarının oran analizi yöntemi ile incelenmesi. Işletme Araştırmaları Dergisi, ˙ 13(1), 912-926, (2021).
• [32] Hitchner, J.R. Financial Valuation Applications and Models (Vol. 545). John Wiley&Sons: New Jersey, (2003).
• [33] Crowther, D. Managing Finance: A Socially Responsible Approach. Elsevier ButterworthHeinemann: Burlington, (2004).
• [34] Akgün, A. BIST enerji şirketlerinin CRITIC ve CODAS bütünleşik yaklaşımı ile finansal açıdan değerlendirilmesi. Selçuk Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 48, 338-356, (2022).
• [35] Osteryoung, J., Constand, R.L. and Nast, D. Financial ratios in large public and small private firms. Journal of Small Business Management, 30(3), 35-46, (1992).
• [36] Akusta, A. Analysis of the relationship between cross capital flows and stock exchange index with machine learning. Abant Sosyal Bilimler Dergisi, 24(1), 244-263, (2024b).
• [37] Supsermpol, P., Thajchayapong, S. and Chiadamrong, N. Predicting financial performance for listed companies in Thailand during the transition period: A class-based approach using logistic regression and random forest algorithm. Journal of Open Innovation: Technology, Market, and Complexity, 9(3), 100130, (2023).
• [38] Singh, S., Gutta, S. and Hadaegh, A. Stock prediction using machine learning. WSEAS Transactions on Computer Research, 9, 152-158, (2021).
• [39] Sivri, M.S., Gultekin, A.B., Ustundag, A., Beyca, O.F., Gurcan, O.F. and Ari, E. A dynamic feature selection technique for the stock price forecasting. In Proceedings, International Conference on Intelligent and Fuzzy Systems, pp. 730-737, Cham: Springer, (2023, August).
• [40] Zhao, H., Sinha, A.P. and Ge, W. Effects of feature construction on classification performance: An empirical study in bank failure prediction. Expert Systems with Applications, 36(2), 2633- 2644, (2009).
• [41] An, Z., Wu, Y., Hao, F., Chen, Y. and He, X. A novel hierarchical feature selection with local shuffling and models reweighting for stock price forecasting. Expert Systems with Applications, 249, 123482, (2024).
• [42] Goto, M. and Sueyoshi, T. Financial ratio analysis: An application to US energy industry. In Productivity, Efficiency, and Economic Growth in the Asia-Pacific Region (pp. 59-79). Heidelberg: Physica-Verlag HD, (2009).
• [43] Ekatah, I., Samy, M., Bampton, R. and Halabi, A. The relationship between corporate social responsibility and profitability: The case of Royal Dutch Shell Plc. Corporate Reputation Review, 14, 249-261, (2011).
• [44] Hughey, C.J. and Sulkowski, A.J. More disclosure= better CSR reputation? An examination of CSR reputation leaders and laggards in the global oil & gas industry. Journal of Academy of Business and Economics, 12(2), 24-34, (2012).
• [45] Gozbasi, O. and Aslan, A. Persistence of profit in energy industry: Dynamic evidence from Turkish companies. International Journal of Economics and Financial Issues, 5(2), 624-628, (2015).
• [46] Fareed, Z., Ali, Z., Shahzad, F., Nazir, M. I. and Ullah, A. Determinants of profitability: Evidence from power and energy sector. Studia Universitatis Babes-Bolyai Oeconomica, 61(3), 59-78, (2016).
• [47] Esmeray, A. and Esmeray, M. The determinants of earnings in Turkey evidence from panel analysis. International Journal of Academic Research in Accounting, Finance and Management Sciences, 6(1), 123-126, (2016).
• [48] Eyüboglu, K. and Çelik, P. Financial performance evaluation of Turkish energy companies with fuzzy AHP and fuzzy TOPSIS methods. Business and economics research Journal, 7(3), 21-37, (2016).
• [49] Metin, S., Yaman, S. and Korkmaz, T. Finansal performansın TOPSIS ve MOORA yöntemleri ile belirlenmesi: BIST enerji firmaları üzerine karşılaştırmalı bir uygulama. ˙ Kahramanmaraş Sütçü Imam Üniversitesi Sosyal Bilimler Dergisi, ˙ 14(2), 371-394, (2017).
• [50] Erduru, I. Elektrik enerjisi sektörünün finansal performans analizi: Türkiye Cumhuriyeti merkez bankası sektör bilançoları üzerine bir araştırma. Işletme Bilimi Kapsamında Sektörel Araştırmalar Iş Dünyasına ve Akademiye Yönelik Değerlendirmeler, SRA Academic Publishing: Isparta, Türkiye, 167-179, (2018).
• [51] Klimenko, R., Naruetharadhol, P. and Ketkaew, C. Determinants of market players’ profitability. The International Journal of Interdisciplinary Organizational Studies, 13(1), 27-35, (2018).
• [52] Bağcı, H. and Yüksel Yiğiter, Ş. BIST’te yer alan enerji şirketlerinin finansal performansının SD ve WASPAS yöntemleriyle ölçülmesi. Bingöl Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 9(18), 877-898, (2019).
• [53] Karcıoğlu, R., Yalçın, S. and Gültekin, Ö.F. Sezgisel Bulanık Mantık ve Entropi tabanlı çok kriterli karar verme yöntemiyle finansal performans analizi: BIST’de işlem gören enerji şirketleri üzerine bir uygulama. MANAS Sosyal Araştırmalar Dergisi, 9(1), 360-372, (2020).
• [54] Ghani, E.K., Rehan, R., Salahuddin, S. and Hye, Q.M.A. Discovering capital structure determinants for SAARC energy firms. International Journal of Energy Economics and Policy, 13(1), 135-143, (2023).
• [55] Yıldırım, I., Özşahin Ş. and Akyüz, K.C. Prediction of the financial return of the paper sector with artificial neural networks. BioResources, 6(4), 4076-4091, (2011).
• [56] Manojlovi´c, T. and Štajduhar, I. Predicting stock market trends using random forests: a sample of the Zagreb stock exchange. In Proceedings, 2015 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pp. 1189-1193, Opatija, Croatia, (2015, May).
• [57] Tekin, S. and Çanakoglu, E. Borsa Istanbul hisse senedi getirilerinin makine öğrenmesi yöntemleriyle tahmini. In Proceedings, 26th Signal Processing and Communications Applications Conference, pp.1-4, Izmir, Türkiye, (2018, July).
• [58] Bhardwaj, N. and Ansari, M.A. Prediction of stock market using machine learning algorithms. International Research Journal of Engineering and Technology, 6(5), 5994-6005, (2019).
• [59] Vijh, M., Chandola, D., Tikkiwal, V. A. and Kumar, A. Stock closing price prediction using machine learning techniques. Procedia Computer Science, 167, 599-606, (2020).
• [60] Öztürkmen, M. and Eren, E. BIST 100 endeksi için yükseliş-düşüş tahmini için bir yapay öğrenme modeli. Efil Journal of Economic Research/Efil Ekonomi Araştırmaları Dergisi, 3(12), 42-52, (2020).
• [61] Roy, S.S., Chopra, R., Lee, K.C., Spampinato, C. and Mohammadi-ivatlood, B. Random forest, gradient boosted machines and deep neural network for stock price forecasting: a comparative analysis on South Korean companies. International Journal of Ad Hoc and Ubiquitous Computing, 33(1), 62-71, (2020).
• [62] Koç Ustalı, N., Tosun, N. and Tosun, Ö. Makine öğrenmesi teknikleri ile hisse senedi fiyat tahmini. Eskişehir Osmangazi Üniversitesi Iktisadi ve Idari Bilimler Dergisi, 16(1), 1-16, (2021).
• [63] Arslankaya, S. and Toprak, Ş. Makine öğrenmesi ve derin öğrenme algoritmalarını kullanarak hisse senedi fiyat tahmini. Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi, 13(1), 178-192, (2021).
• [64] Reddy, P.V. and Kumar, S.M. A novel approach to improve accuracy in stock price prediction using gradient boosting machines algorithm compared with Random Forest algorithm. In Proceedings, AIP Conference Proceedings (Vol. 2822, No. 1), pp. 1-8, (2023, November).
• [65] Hu, Q., Qin, S. and Zhang, S. Comparison of stock price prediction based on different machine learning approaches. In Proceedings, 2022 International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022), pp. 215-231, Wuhan, Hubei Province, China, (2022, December).
• [66] Leippold, M., Wang, Q. and Zhou, W. Machine learning in the Chinese stock market. Journal of Financial Economics, 145(2), 64-82, (2022).
• [67] Nakagawa, K. and Yoshida, K. Time-series gradient boosting tree for stock price prediction. International Journal of Data Mining, Modelling and Management, 14(2), 110-125, (2022).
• [68] Shrivastav, L.K. and Kumar, R. An ensemble of random forest gradient boosting machine and deep learning methods for stock price prediction. Journal of Information Technology Research (JITR), 15(1), 1-19, (2022).
• [69] Akyol Özcan, K. Borsa endeksi yönünün makine öğrenmesi yöntemleri ile tahmini: BIST 100 örneği. Gümüşhane Üniversitesi Sosyal Bilimler Dergisi, 14(3), 1001-1018, (2023).
• [70] Hartanto, A.D., Kholik, Y.N. and Pristyanto, Y. Stock price time series data forecasting using the light gradient boosting machine (LightGBM) model. International Journal on Informatics Visualization, 7(4), 2270-2279, (2023).
• [71] Kesharwani, H., Mallick, T., Nakarmi, A. and Raj, G. Evaluation of stock prices prediction using recent machine learning algorithms. In Proceedings, International Conference on Advances and Applications of Artificial Intelligence and Machine Learning, pp. 557-566, Singapore, Springer, (2023).
• [72] Toprak, Ş., Çağıl, G. and Kökçam, A.H. Stock closing price prediction with machine learning algorithms: PETKM stock example in BIST. Düzce University Journal of Science & Technology, 11(2), 958-976, (2023).
• [73] Rastogi, R., Jaiswal, R. and Jaiswal, R.K. Renewable energy firm’s performance analysis using machine learning approach. Procedia Computer Science, 175, 500-507, (2020).
• [74] Sutton, C.D. Classification and regression trees, bagging, and boosting. Handbook of Statistics, 24, 303-329, (2005).
• [75] Prasad, A.M., Iverson, L.R. and Liaw, A. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems, 9, 181-199, (2006).
• [76] Abedi, R., Costache, R., Shafizadeh-Moghadam, H. and Pham, Q.B. Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees. Geocarto International, 37(19), 5479-5496, (2022).
• [77] Carty, D.M., Young, T.M., Zaretzki, R.L., Guess, F.M. and Petutschnigg, A. Predicting and correlating the strength properties of wood composite process parameters by use of boosted regression tree models. Forest Products Journal, 65(7-8), 365-371, (2015).
• [78] Ceperic, V., Gielen, G. and Baric, A. Sparse ε-tube support vector regression by active learning. Soft Computing, 18, 1113-1126, (2014).
• [79] Pratheepan, T. A panel data analysis of profitability determinants: Empirical results from Sri Lankan manufacturing companies. International Journal of Economics, Commerce and Management, 2(12), 1-9, (2014).
• [80] Singh, N.P. and Bagga, M. The effect of capital structure on profitability: An empirical panel data study. Jindal Journal of Business Research, 8(1), 65-77, (2019).