Kredi Riski Sınıflandırmasında Kelimelerin Gücü: Alternatif Kredi Derecelendirme Aracı Olarak Sentiment Analizi
DOI:
https://doi.org/10.37241/jatss.2026.149Anahtar Kelimeler:
kredi derecelendirme raporları- kredi notu tahmini- transformer tabanlı sınıflandırma- finansal doğal dil işlemeÖzet
Giriş: Bu çalışma, kredi derecelendirme raporlarında yer alan nitel anlatıların makine öğrenmesi ile sistematik biçimde yapılandırılıp yapılandırılamayacağını ve bu anlatıdan türetilen göstergelerin ulusal kredi notunu öngörmede ne ölçüde bilgi taşıdığını incelemektedir. Araştırma, derecelendirme süreçlerinde merkezi rol oynayan ancak çoğu zaman nicel modellere doğrudan entegre edilemeyen anlatı temelli değerlendirmeleri ölçülebilir ve analitik olarak işlenebilir hale getirmesi bakımından önemlidir.
Yöntem: Bu çalışma, kamuya açık kurumsal kredi derecelendirme raporlarını incelemektedir. Raporlardaki ifadeler transformer tabanlı bir modelle güçlü yönler ve kısıtlar olarak sınıflandırılarak anlatı göstergelerine dönüştürülmüştür. Yalnızca bu özellikler kullanılarak ulusal kredi notu çok sınıflı bir problem olarak tahmin edilmiş, veri sızıntısını önlemek için firma bazlı ayrım uygulanmış ve performans accuracy, precision, recall ve F1-skoru ile değerlendirilmiştir.
Sonuçlar ya da Bulgular: Güçlü yönler-kısıtlar sınıflandırması yüksek performans üretmiştir (accuracy=0,977; F1=0,981). Ulusal kredi notu tahmininde ise örneklem dışı doğruluk 0,517; macro-F1 0,403; weighted-F1 0,500 olarak elde edilmiştir. Sınıf bazında AA (F1=0,605) ve BBB (F1=0,591) sınıflarında görece daha istikrarlı sonuçlar görülürken, AAA’da düşük duyarlılık ve BB’de düşük destek nedeniyle zayıf performans dikkat çekmektedir.
Tartışma ya da Yapılan Çıkarımlar: Bulgular, rapor anlatılarından türetilen göstergelerin kredi notuna ilişkin anlamlı ancak tek başına yeterli olmayan bir sinyal taşıdığını göstermektedir. Önerilen yaklaşım, yeni yayımlanan raporların hızlı özetlenmesi, güçlü yönler-kısıtlar dengesindeki değişimlerin izlenmesi ve ölçeklenebilir kredi gözetimi/erken uyarı sistemleri için kullanılabilir. Gelecek araştırmaların, anlatı göstergelerini finansal ve makro değişkenlerle birleştirmesi gibi yöntemler önerilmektedir.
İndirmeler
Referanslar
Aksoy, B. (2020). Sigorta şirketlerinin derecelendirilmesinde makine öğrenmesi yöntemleri tahmin performansının karşılaştırılması: Türkiye örneği. Akademik Araştırmalar ve Çalışmalar Dergisi (AKAD), 12(23), 579-597. https://doi.org/10.20990/kilisiibfakademik.710863
Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., & Vanthienen, J. (2003). Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the Operational Research Society, 54(6), 627–635. https://doi.org/10.1057/palgrave.jors.2601545
Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.
Boughaci, D., & Alkhawaldeh, A. A. K. (2020). Appropriate machine learning techniques for credit scoring and bankruptcy prediction in banking and finance: A comparative study. Risk and Decision Analysis, 8(1–2), 15–24. https://doi.org/10.3233/RDA-180051
Bucker, M., Szepannek, G., Gosiewska, A., & Biecek, P. (2022). Transparency, auditability, and explainability of machine learning models in credit scoring. Journal of the Operational Research Society, 73(1), 70–90. https://doi.org/10.1080/01605682.2021.1922098
Chen, Y.-J., & Chen, Y.-M. (2022). Forecasting corporate credit ratings using big data from social media. Expert Systems with Applications, 207, Article 118042. https://doi.org/10.1016/j.eswa.2022.118042
Darwish, J. A. (2025). Optimization and prediction of corporate credit rating through advanced feature selection based on AI and deep learning. Alexandria Engineering Journal, 127, 586–594. https://doi.org/10.1016/j.aej.2025.05.043
De Oliveira, N. A., & Basso, L. F. C. (2025). Advancing credit rating prediction: The role of machine learning in corporate credit rating assessment. Risks, 13(6), 116. https://doi.org/10.3390/risks13060116
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In J. Burstein, C. Doran, & T. Solorio (Eds.), Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long and Short Papers) (pp. 4171–4186). Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
Doğan, S., Büyükkör, Y., & Atan, M. (2022). A comparative study of corporate credit ratings prediction with machine learning. Operations Research and Decisions, 32(1), 25–47. https://doi.org/10.37190/ord220102
Dumitrescu, E., Hué, S., Hurlin, C., & Tokpavi, S. (2022). Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects. European Journal of Operational Research, 297(3), 1178–1192. https://doi.org/10.1016/j.ejor.2021.06.053
Fei, W., Gu, J., Yang, Y., & Zhou, Z. (2015). Credit risk evaluation based on social media. Procedia Computer Science, 55, 725–731. https://doi.org/10.1016/j.procs.2015.07.165
Gajdosikova, D., & Valaskova, K. (2023). Bankruptcy prediction model development and its implications on financial performance in Slovakia. Economics and Culture, 20(1), 30– 42. https://doi.org/10.2478/jec-2023-0003
Gambacorta, L., Huang, Y., Qiu, H., & Wang, J. (2024). How do machine learning and nontraditional data affect credit scoring? New evidence from a Chinese fintech firm. Journal of Financial Stability, 73, Article 101284. https://doi.org/10.1016/j.jfs.2024.101284
Gunnarsson, B. R., vanden Broucke, S., Baesens, B., Óskarsdóttir, M., & Lemahieu, W. (2021). Deep learning for credit scoring: Do or don’t? European Journal of Operational Research, 295(1), 292–305. https://doi.org/10.1016/j.ejor.2021.03.006
Gül, S., Kabak, Ö., & Topcu, I. (2018). A multiple criteria credit rating approach utilizing social media data. Data & Knowledge Engineering, 116, 80–99. https://doi.org/10.1016/j.datak.2018.05.005
Issa, S., Bizel, G., Jagannathan, S. K., & Gollapalli, S. S. C. (2024). A comprehensive approach to bankruptcy risk evaluation in the financial industry. Journal of Risk and Financial Management, 17(1), 41. https://doi.org/10.3390/jrfm17010041
Lessmann, S., Baesens, B., Seow, H.-V., & Thomas, L. C. (2015). Benchmarking state-of-theart classification algorithms for credit scoring: An update of research. European Journal of Operational Research, 247(1), 124–136. https://doi.org/10.1016/j.ejor.2015.05.030
Liu, B. (2012). Sentiment analysis and opinion mining. Morgan & Claypool Publishers.
Liu, Y., & Schumann, M. (2005). Data mining feature selection for credit scoring models. The Journal of the Operational Research Society, 56(9), 1099–1108. https://doi.org/10.1057/palgrave.jors.2601976
Machado, M. R., & Karray, S. (2022). Assessing credit risk of commercial customers using hybrid machine learning algorithms. Expert Systems with Applications, 200, Article 116889. https://doi.org/10.1016/j.eswa.2022.116889
Machado, M. R., Chen, D. T., & Osterrieder, J. R. (2025). An analytical approach to credit risk assessment using machine learning models. Decision Analytics Journal, 16, Article 100605. https://doi.org/10.1016/j.dajour.2025.100605
Marqués, A. I., García, V., & Sánchez, J. S. (2012). Two-level classifier ensembles for credit risk assessment. Expert Systems with Applications, 39(12), 10916–10922. https://doi.org/10.1016/j.eswa.2012.03.033
Máté, D., Raza, H., & Ahmad, I. (2023). Comparative analysis of machine learning models for bankruptcy prediction in the context of Pakistani companies. Risks, 11(10), Article 176. https://doi.org/10.3390/risks11100176
Muñoz-Izquierdo, N., Segovia-Vargas, M. J., Camacho-Miñano, M.-M., & Pérez-Pérez, Y. (2022). Machine learning in corporate credit rating assessment using the expanded audit report. Machine Learning, 111(11), 4183–4215. https://doi.org/10.1007/s10994-02206226-4
Pai, P.-F., Tan, Y.-S., & Hsu, M.-F. (2015). Credit rating analysis by the decision-tree support vector machine with ensemble strategies. International Journal of Fuzzy Systems, 17(4), 521–530. https://doi.org/10.1007/s40815-015-0063-y
Paleologo, G., Elisseeff, A., & Antonini, G. (2010). Subagging for credit scoring models. European Journal of Operational Research, 201(2), 490–499. https://doi.org/10.1016/j.ejor.2009.03.008
Pang, B., & Lee, L. (2008). Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1–2), 1–135. https://doi.org/10.1561/1500000001
Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37–63. https://doi.org/10.9735/2229-3981
Prottasha, N. J., Sami, A. A., Kowsher, M., Murad, S. A., Bairagi, A. K., Masud, M., & Baz, M. (2022). Transfer learning for sentiment analysis using BERT based supervised finetuning. Sensors, 22(11), 4157. https://doi.org/10.3390/s22114157
Radovanovic, J., & Haas, C. (2023). The evaluation of bankruptcy prediction models based on socio-economic costs. Expert Systems with Applications, 227, Article 120275. https://doi.org/10.1016/j.eswa.2023.120275
Saberi, B., & Saad, S. (2017). Sentiment analysis or opinion mining: A review. .International Journal of Advanced Science Engineering Information Technology, 7(5), 1660-1666.
Siham, A., Sekkate, S., & Adib, A. (2021). Feature selection based on machine learning for credit scoring: An evaluation of filter and embedded methods. In Z. H. Kilimci, T. Yildirim, V. Piuri, I. Czarnowski, D. Camacho, Y. Manolopoulos, & S. Solak (Eds.), Proceedings of the 2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA 2021) (pp. 1–6). IEEE. https://doi.org/10.1109/INISTA52262.2021.9548410
Slapnik, U., & Lončarski, I. (2023). Understanding sovereign credit ratings: Text-based evidence from the credit rating reports. Journal of International Financial Markets, Institutions and Money, 88, Article 101838. https://doi.org/10.1016/j.intfin.2023.101838
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002
Sugozu, I. H., Verberi, C., & Yasar, S. (2025). Machine learning approaches to credit risk: Evaluating Turkish participation and conventional banks. Borsa Istanbul Review, 25(3), 497-512. https://doi.org/10.1016/j.bir.2025.02.001
Teles, G., Rodrigues, J. J. P. C., Rabêlo, R. A. L., & Kozlov, S. A. (2021). Comparative study of support vector machines and random forests machine learning algorithms on credit operation. Software: Practice and Experience, 51(12), 2492–2500. https://doi.org/10.1002/spe.2842
Teles, G., Rodrigues, J. J. P. C., Saleem, K., Kozlov, S., & Rabêlo, R. A. L. (2020). Machine learning and decision support system on credit scoring. Neural Computing and Applications, 32(14), 9809–9826. https://doi.org/10.1007/s00521-019-04537-7
Thomas, L. C. (2000). A survey of credit and behavioural scoring: Forecasting financial risk of lending to consumers. International Journal of Forecasting, 16(2), 149–172.
https://doi.org/10.1016/S0169-2070(00)00034-0
Toudas, K., Archontakis, S., & Boufounou, P. (2024). Corporate bankruptcy prediction models: A comparative study for the construction sector in Greece. Computation, 12(1), 9. https://doi.org/10.3390/computation12010009
Tripathi, D., Edla, D. R., Cheruku, R., & Kuppili, V. (2019). A novel hybrid credit scoring model based on ensemble feature selection and multilayer ensemble classification. Computational Intelligence, 35(2), 371–394. https://doi.org/10.1111/coin.12200
Tripathi, D., Edla, D. R., Kuppili, V., & Bablani, A. (2020). Evolutionary extreme learning machine with novel activation function for credit scoring. Engineering Applications of Artificial Intelligence, 96, Article 103980. https://doi.org/10.1016/j.engappai.2020.103980
Trivedi, S. K. (2020). A study on credit scoring modeling with different feature selection and machine learning approaches. Technology in Society, 63, Article 101413. https://doi.org/10.1016/j.techsoc.2020.101413
Tsai, C.-F. (2014). Combining cluster analysis with classifier ensembles to predict financial distress. Information Fusion, 16, 46–58. https://doi.org/10.1016/j.inffus.2011.12.001
Wang, G., Hao, J., Ma, J., & Jiang, H. (2011). A comparative assessment of ensemble learning for credit scoring. Expert Systems with Applications, 38(1), 223–230. https://doi.org/10.1016/j.eswa.2010.06.048
Wu, Y., & Pan, Y. (2021). Application analysis of credit scoring of financial institutions based on machine learning model. Complexity, 2021(1), Article 9222617. https://doi.org/10.1155/2021/9222617
Xu, Y., Chen, Y., Sun, L., & Chen, Y. (2025). Corporate credit scoring method based on unlabeled data and multi-source data. Decision Support Systems, 198, Article 114543. https://doi.org/10.1016/j.dss.2025.114543
Yobas, M. B., Crook, J. N., & Ross, P. (2000). Credit scoring using neural and evolutionary techniques. IMA Journal of Management Mathematics, 11(2), 111-125. https://doi.org/10.1093/imaman/11.2.11
İndir
Yayınlanmış
Nasıl Atıf Yapılır
Sayı
Bölüm
