Financial Predictions Using Cost Sensitive Neural Networks for Multi-Class Learning

Abstract:

The interest in the localisation of wireless sensor networks has grown in recent years. A variety of machine-learning methods have been proposed in recent years to improve the optimisation of the complex behaviour of wireless networks. Network administrators have found that traditional classification algorithms may be limited with imbalanced datasets. In fact, the problem of imbalanced data learning has received particular interest. The purpose of this study was to examine design modifications to neural networks in order to address the problem of cost optimisation decisions and financial predictions. The goal was to compare four learning-based techniques using cost-sensitive neural network ensemble for multiclass imbalance data learning. The problem is formulated as a combinatorial cost optimisation in terms of minimising the cost using meta-learning classification rules for Naïve Bayes, J48, Multilayer Perceptions, and Radial Basis Function models. With these models, optimisation faults and cost evaluations for network training are considered.

• Periodical: Advanced Engineering Forum (Volume 16)
• Pages: 104-116
• DOI: https://doi.org/10.4028/www.scientific.net/AEF.16.104
• Online since: April 2016
• Authors: Eleni Rozaki*
• Keywords: Artificial Network Modelling, Cost Sensitive Neural Networks, Multi-Class Learning, Multilayer Perceptron, Radial Basis Function

References

[1] P. Cao, D. Zhao and O. Zaiane, Measure optimized cost-sensitive neural network ensemble for multiclass imbalance data learning. 2013 13th International Conference on Hybrid Intelligent Systems. (2013) 35-40.

DOI: 10.1109/his.2013.6920500

[2] C. Charnay, N. Lachiche and A. Braud, Pairwise optimization of bayesian classifiers for multi-class cost-sensitive learning, 2013 IEEE 25th International Conference on Tools with Artificial Intelligence. (2013) 499-505.

DOI: 10.1109/ictai.2013.80

[3] J. Kim, K. Choi, G. Kim and Y. Suh, Classification cost: An empirical comparison among traditional classifier, cost-sensitive classifier, and metacost, Expert Systems with Applications. 39, 4 (2012) 4013-4019.

DOI: 10.1016/j.eswa.2011.09.071

[4] N. Loukeris. Radial basis functions networks to hybrid neuro-genetic RBFNs in financial evaluation of corporations. 12 WSEAS International Conference on Computers. (2008) 812-819.

[5] M. Adler, R. K. Sitaraman and H. Venkataramani, Algorithms for optimizing the bandwidth cost of content delivery, Computer Networks. 55, 8 (2011) 4007-4020.

DOI: 10.1016/j.comnet.2011.07.015

[6] D. Gabel, An application of stand-along costs to the telecommunications industry, Telecommunications Policy. 15, 1, (1991) 75-84.

DOI: 10.1016/0308-5961(91)90045-d

[7] V. Lopez, S del Rio, J. M. Benitez and f. Herrera, Cost-sensitive linguistic fuzzy role based classification systems under the MapReduce framework for imbalanced big data, Fuzzy Sets and Systems. 258 (2015) 5-38.

DOI: 10.1016/j.fss.2014.01.015

[8] P. N. Um, L. Gille, L. Simon and C. Rudelle, A Model for calculating interconnection costs in Telecommunications. Washington, D.C.: The World Bank. (2004).

DOI: 10.1596/0-8213-5671-2

[9] B. Haider, M. Zafrullah and M. K. Islam, Radio frequency optimization & QoS evaluation in operational gsm network, Proceedings of the World Congress on Engineering and Computer Science. (2009) 393-398.

[10] C. K. Walgampaya and M. Kantardzic, Cost-sensitive analysis in multiple time series prediction, Conference on Data Mining. (2006) 17-23.

[11] S. IIiya, E. Goodyer, J. Gow, J. Shell and M. Gongora. Application of artificial neural network and support vector regression in cognitive radio networks for RF power prediction using compact differential evolution algorithm, Proceedings of the Federated Conference on Computer Science and Information Systems. 5 (2015).

DOI: 10.15439/2015f14

[12] E. Rozaki, Design and implementation for automated network troubleshooting using data mining, International Journal of Data Mining & Knowledge Management Process (IJDKP). 5 (2015) 9-27.

DOI: 10.5121/ijdkp.2015.5302

[13] E. Rozaki, Clustering optimisation techniques in mobile networks, International Journal on Recent and Innovation Trends in Computing and Communication (IJRITCC). 4, 2, (2016) 22 – 29.

[14] C. Ferri-Ramirez, P. Flach and J. Hernandez-Orallo, Multi-dimensional roc analysis with decision trees, Technical Report. (2002) 1-36.

[15] Y. Gao and J. Wang, Active learning method of bayesian networks classifier based on cost-sensitive sampling, 2011 IEEE International Conference on Computer Science and Automation Engineering. (2011) 233-236.

DOI: 10.1109/csae.2011.5952671

[16] Z. Xu, M. J. Kusner, K. Q. Weinberger, M. Chen and O. Chapelle, Classifier cascades and trees for minimizing feature evaluation cost, Journal of Machine Learning Research. 15 (2014) 2113-2144.

[17] L. Zeng, B. Veeravalli and X Li, SABA: A security-aware and budget-aware workflow scheduling strategy in clouds, Journal of Parallel and Distributed Computing. 75 (2015) 141-151.

DOI: 10.1016/j.jpdc.2014.09.002

[18] T. Kihara, N. Tateishi and S. Seto, Evaluation of network fault-detection method based on anomaly detection with matrix eigenvector, 2011 13th Asia-Pacific Network Operations and Management Symposium. (2011) 1-7.

DOI: 10.1109/apnoms.2011.6077024

[19] R. Arora and Suman, Comparative analysis of classification algorithms on different datasets using WEKA. International Journal of Computer Applications. 54, 13 (2012) 21-25.

DOI: 10.5120/8626-2492