Designing Early Warning System: Prediction Accuracy of Currency Crisis by Using k-Nearest Neighbour Method

Authors: Nor Azuana Ramli, Mohd Tahir Ismail, Hooy Chee Wooi

Abstract:

Developing a stable early warning system (EWS) model that is capable to give an accurate prediction is a challenging task. This paper introduces k-nearest neighbour (k-NN) method which never been applied in predicting currency crisis before with the aim of increasing the prediction accuracy. The proposed k-NN performance depends on the choice of a distance that is used where in our analysis; we take the Euclidean distance and the Manhattan as a consideration. For the comparison, we employ three other methods which are logistic regression analysis (logit), back-propagation neural network (NN) and sequential minimal optimization (SMO). The analysis using datasets from 8 countries and 13 macro-economic indicators for each country shows that the proposed k-NN method with k = 4 and Manhattan distance performs better than the other methods.

Keywords: Currency crisis, k-nearest neighbour method, logit, neural network.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1087229

References:

[1] M. Gassner, B. Brabec, “Nearest neighbour models for local and regional avalanche forecasting,” Natural Hazards and Earth System Sciences, Vol. 2, pp. 247-253, 2002.
[2] Quansheng Kuang, Lei Zhao, “A practical GPU based kNN algorithm,” in Proc. 2nd International Computer Science and Computational Technology, China, 2009, pp. 151-155.
[3] Javier Arroyo, Carlos Maté, “Forecasting histogram time series with knearest neighbours methods,” International Journal of Forecasting, vol. 25, pp. 192-207, 2009.
[4] Madhavi Pradhan, “Design of Classifier for Detection of Diabetes using Neural Network and Fuzzy k-Nearest Neighbor Algorithm,” International Journal of Computational Engineering Research, vol. 2, no. 5, pp. 1384-1387, Sept. 2012.
[5] Jieh-Haur Chen, “KNN based knowledge-sharing model for severe change order disputes in construction,” Automation in Construction, vol. 17, pp. 773-779, 2008.
[6] Jae H. Min, Young-Chan Lee, “Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters,” Journal Expert Systems with Applications, vol.28, pp. 603-614, 2005.
[7] James C. Bezdek, Siew K. Chuah, “Generalized k-nearest neighbour rules,” Fuzzy Sets and Systems, vol.18, no.3, pp. 237-256, 1986.
[8] Shixin Yu et al., “Genetic feature selection combined with composite fuzzy nearest neighbor classifiers for hyperspectral satellite imagery,” Pattern Recognition Letters, vol. 23, pp. 183-190, 2002.
[9] Lamartine Almeida Teixeira, Adriano Lorena, “A method for automatic stock trading combining technical analysis and nearest neighbor classification,” Expert Systems with Applications, vol. 37, pp. 6885- 6890, 2010.
[10] S. Arya et al., “An optimal algorithm for approximate nearest neighbor searching fixed dimensions,” Journal of the ACM, vol. 45, no. 6, pp. 891-923, 1998.
[11] K. Q.. Weinberger, L.K. Saul, “Distance metric learning for large margin nearest neighbor classification,” Journal of Machine Learning Research, vol.10, pp. 207-244, 2009.
[12] J. Goldberger et al., “Neighbourhood components analysis,” in Proceedings of the Conference on Neural Information Processing Systems, 2004.
[13] Lutz Hamel, Knowledge Discovery with Support Vector Machines. New Jersey: A John-Wiley & Sons, 2009.
[14] Ethem Alpaydin, Introduction to Machine Learning, 2nd ed. Massachusetts: The MIT Press, 2010.
[15] Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York: Springer-Verlag, 2008.
[16] C. M. Bishop, Pattern Recognition and Machine Learning. New York: Springer-Verlag, 2007.
[17] WEKA – www.cs.waikato.ac/nz/ml/weka