İŞLETMELERİN İFLAS TAHMİNİNDE K- EN YAKIN KOMŞU ALGORİTMASI ÜZERİNDEN UZAKLIK ÖLÇÜTLERİNİN KARŞILAŞTIRILMASI

Makine öğrenmesi biyoteknoloji alanından eğitim bilimlerine, doğal dil işlemeden duygu analizine kadar medikal, eğitim, işletme gibi birçok alanda aktif olarak kullanılan bir disiplindir. Kullanım alanı genişledikçe regresyon, sınıflama, kümeleme gibi farklı problemlere çözüm arayan makine öğrenmesi, iflas tahmini probleminde de kullanılmaya başlamıştır. Makine öğrenmesi disiplininde algoritma sayısı arttıkça, parametreler değiştikçe farklı doğruluk oranlarına ulaşmak mümkündür. Bu amaçla, çalışmada k En Yakın Komşu algoritmasına yer verilmiş; farklı uzaklık ölçütleri (Euclidean, Manhattan, Chebysev, Minkowski) kullanılarak yapılan sınıflandırma işlemi sonucunda en yüksek doğruluk oranına sahip uzaklık ölçütü belirlenmiştir. Veri seti %70 eğitim- %30 test seti olarak bölünmüş; çeşitli performans ölçütleri kullanılarak algoritmalar birbiriyle karşılaştırılmıştır.

Anahtar Kelimeler:

iflas tahmini, k-en yakın komşu, makine öğrenmesi, uzaklık ölçütleri

COMPARISON STUDY OF DISTANCE MEASURES USING K- NEAREST NEIGHBOR ALGORITHM ON BANKRUPTCY PREDICTION

Machine learning is a discipline that is actively used in many areas such as medical, education and business management, from biotechnology to educational science, natural language processing to emotion analysis. As the area of use expanded, machine learning, which was looking for solutions to different problems such as regression, classing and clustering, also started to be used in the problem of bankruptcy prediction. As the number of algorithms increases in machine learning discipline, it is possible to achieve different accuracy rates as parameters change. For this purpose, the k Nearest Neighbor algorithm was involved in our study and the distance measure with the best accuracy were determined as a result of the classification process using different distance measures (Euclidean, Manhattan, Chebysev, Minkowski). The data set is divided into 70% training - 30% test; algorithms are compared using various performance criteria.

Keywords:

bankruptcy prediction, distance measures, machine learning, k-nearest neighbor,

PDF

___

Alpaydin, E. (2010). Introduction to machine learning (2nd ed). MIT Press.
Altman, E. I., & Hotchkiss, E. (2006). Corporate Financial Distress and Bankruptcy (Third Edition).
Back, B. (1996). Choosing Bankruptcy Predictors Using Discriminant Analysis, Logit Analysis, and Genetic Algorithms. 20.
Balcaen, S., & Ooghe, H. (2006). 35 years of studies on business failure: An overview of the classic statistical methodologies and their related problems. The British Accounting Review, 38(1), 63-93. https://doi.org/10.1016/j.bar.2005.09.001
Bulut, F., & Osmani, S. (2017). Scene Change Detection using Different Color Pallets and Performance Comparison. Balkan Journal of Electrical and Computer Engineering, 66-72. https://doi.org/10.17694/bajece.336217
Han, J., Kamber, M., & Pei, J. (2011). Data Mining Concepts and Techniques Third Edition (Third Edition). Morgan Kaufmann.
Hastie, T., friedman, J., & Tibshirani, R. (2008). Unsupervised Learning. In: The Elements of Statistical Learning. https://doi.org/10.1007/978-0-387-84858-7_14
Hu, L.-Y., Huang, M.-W., Ke, S.-W., & Tsai, C.-F. (2016). The distance function effect on k-nearest neighbor classification for medical datasets. SpringerPlus, 5(1), 1304. https://doi.org/10.1186/s40064-016-2941-7
Khan, M., Ding, Q., & Perrizo, W. (2002). K-nearest Neighbor Classification on Spatial Data Streams Using P-trees. Advances in Knowledge Discovery and Data Mining, 2336, 517-528. https://doi.org/10.1007/3-540-47887-6_51
Korol, T. (2019). Dynamic Bankruptcy Prediction Models for European Enterprises. Journal of Risk and Financial Management, 12(4), 185. https://doi.org/10.3390/jrfm12040185
Kotsiantis, S. B. (2007). Supervised Machine Learning: A Review of Classification Techniques. 20.
Liang, D., Lu, C.-C., Tsai, C.-F., & Shih, G.-A. (2016). Financial ratios and corporate governance indicators in bankruptcy prediction: A comprehensive study. European Journal of Operational Research, 252(2), 561-572. https://doi.org/10.1016/j.ejor.2016.01.012
Mitchell, T. M. (2006). The Discipline of Machine Learning.
Prasath, V. B. S., Alfeilat, H. A. A., Hassanat, A. B. A., Lasassmeh, O., Tarawneh, A. S., Alhasanat, M. B., & Salman, H. S. E. (2019). Distance and Similarity Measures Effect on the Performance of K-Nearest Neighbor Classifier—A Review. Big Data, 7(4), 221-248. https://doi.org/10.1089/big.2018.0175
Thian Cheng Lim, Lim Xiu Yun, J., Siwei, G., & Jiang, H. (2012). Bankruptcy Prediction: Theoretical Framework Proposal. International Journal of Management Sciences and Business Research, 1(9), 69-74.
UCI, https://archive.ics.uci.edu/ml/datasets/Taiwanese+Bankruptcy+Prediction, Erişim Tarihi: 25.08.2020
Weber, M. (2000). Unsupervised Learning of Models for Object Recognition. 127.
Weinberger, K. Q., Blitzer, J., & Saul, L. K. (t.y.). Distance Metric Learning for Large Margin Nearest Neighbor Classification. 8.