THERMAL SCIENCE

International Scientific Journal

External Links

REVISITING DISTANCE METRICS IN K-NEAREST NEIGHBORS ALGORITHMS: IMPLICATIONS FOR SOVEREIGN COUNTRY CREDIT RATING ASSESSMENTS

ABSTRACT
The k-nearest neighbors (k-NN) algorithm, a fundamental machine learning technique, typically employs the Euclidean distance metric for proximity-based data classification. This research focuses on the feature importance infused k-NN model, an advanced form of k-NN. Diverging from traditional algorithm uniform weighted Euclidean distance, feature importance infused k-NN introduces a specialized distance weighting system. This system emphasizes critical features while reducing the impact of lesser ones, thereby enhancing classification accuracy. Empirical studies indicate a 1.7% average accuracy improvement with proposed model over conventional model, attributed to its effective handling of feature importance in distance calculations. Notably, a significant positive correlation was observed between the disparity in feature importance levels and the model's accuracy, highlighting proposed model’s proficiency in handling variables with limited explanatory power. These findings suggest proposed model’s potential and open avenues for future research, particularly in refining its feature importance weighting mechanism, broadening dataset applicability, and examining its compatibility with different distance metrics.
KEYWORDS
PAPER SUBMITTED: 2023-11-11
PAPER REVISED: 2024-01-30
PAPER ACCEPTED: 2024-02-01
PUBLISHED ONLINE: 2024-02-18
DOI REFERENCE: https://doi.org/10.2298/TSCI231111008C
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2024, VOLUME 28, ISSUE Issue 2, PAGES [1905 - 1915]
REFERENCES
  1. Kalaiarasi, K.. et al., Optimization of the Average Monthly Cost of an EOQ Inventory Model for Deteriorating Items in Machine Learning Using PYTHON, Thermal Science, 25 (2022). Special Issue 2, pp. 347-358
  2. Cheng, Debo., et al., k-NN Algorithm with Data-Driven k Value, Proceedings, 10th Advanced Data Mining and Applications: 10th International Conference, Guilin, China, 2014, pp. 499-512
  3. Zhang, S., Challenges in KNN Classification, IEEE Transactions on Knowledge and Data Engineering. 34 (2022), 10, pp. 4663-4675
  4. Dastile, X., et al., Statistical and Machine Learning Models in Credit Scoring: A Systematic Literature Survey, Applied Soft Computing, 91 (2020), 106263
  5. Mladenova, T., A Feature-Weighted Rule for the k-Nearest Neighbor, Proceedings, 5th Int. Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Bolu, Turkey, 2021, pp. 493-497
  6. Liang, J., An Ensemble Method, Proceedings, 4th International Conference on Communication and Information Processing, New York, USA, 2018, pp. 186-190
  7. Huang, J., et al., An Improved k-NN Based on Class Contribution and Feature Weighting, Proceedings, 10th International Conference on Measuring Technology and Mechatronics Automation, Changsha, China, 2018, pp. 313-316
  8. +++, School of Computing and Information Sciences, archive.ics.uci.edu/ml
  9. Liangxiao, J., et al., Bayesian Citation-kNN with Distance Weighting, International Journal of Machine Learning and Cybernetics, 5 (2014), 2, pp. 193-199
  10. Biswas, N., et al., A Parameter Independent Fuzzy Weighted k-Nearest Neighbor Classifier, Pattern Recognition Letters, 101 (2018), Jan., pp. 80-87
  11. Peng, X., et al., An Improved Weighted k-Nearest Neighbor Algorithm for Indoor Localization, Electronics, 9 (2020), 12, 2117
  12. Ertugrul, O. F., A Novel Distance Metric Based on Differential Evolution, Arabian Journal for Science and Engineering, 44 (2019), July, pp. 9641-9651
  13. Alsakka, R., Gwilym, O., Leads and Lags in Sovereign Credit Ratings, Journal of Banking & Finance, 34 (2010), 11, pp. 2614-2626
  14. Ahmed, S. E., Cetin, A. I., Determinants of Credit Ratings and Comparison of the Rating Prediction Performances of Machine Learning Algorithms, Proceedings, 17th E3S Web of Conferences, Cape Town, South Africa, 2023, Vol. 409, 05013
  15. Ekmekcioglu, M., et al., Predicting Sovereign Credit Ratings Using Machine Learning Algorithms, Proceedings, 1st Industrial Eng. in the Covid-19 Era: Selected Papers from the Hybrid Global Joint Conference on Industrial Eng. and Its Application Areas, GJCIE 2022, Switzerland, 2023, pp. 52-61
  16. Takawira, O., Mwamba, J. W. M., Sovereign Credit Ratings Analysis Using the Logistic Regression Model, Risks, 10 (2022), 4, pp. 70-93
  17. +++, Worldbank Databank, databank.worldbank.org/home.aspx
  18. +++, Human Development Reports, hdr.undp.org/data-center
  19. Ali, N., et al., Evaluation of k-Nearest Neighbour Classifier Performance for Heterogeneous Data Sets, SN Applied Sciences, 1 (2019), Nov., 1559
  20. Obiedat, R., et al., An Intelligent Hybrid Sentiment Analyzer for Personal Protective Medical Equipments Based on Word Embedding Technique: The COVID-19 Era, Symmetry, 13 (2021), 12, 2287
  21. Gothai, E., et al., Map-Reduce based Distance Weighted k-Nearest Neighbor Machine Learning Algorithm for Big Data Applications, Scalable Computing, Practice and Experience, 23 (2022), 4, pp. 129-145
  22. Bajpai, A., et al., Performance Enhancement of Automatic Speech Recognition System Using Euclidean Distance Comparison and Artificial Neural Network, Proceedings, 3th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU), Bhimtal, India, IEEE 2018, pp. 1-5
  23. Abdulrahim, H., et al., Machine Learning Models to Prediction OPIC Crude Oil Production, Thermal Science, 26 (2022), Special Issue 1, pp. 437-443

© 2024 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence