Companies Trading Signs Prediction Using Fuzzy Hybrid Operator with Swarm Optimization Algorithms

Companies with the Trading Suspension (SP), and Non-Compliance (NC) sign posted might run a risk of bankruptcy. One would want to predict the SP or NC sign posted before it is posted to help in investing decision. In this paper, we introduce the prediction system using fuzzy hybrid operator with swarm intelligence optimization algorithm. In particular, we utilize the gamma operator with firefly, grey wolf, and social spider algorithms. The gamma operator with social spider yields 92.45% correct prediction result. We also compare our result with the support vector machine (SVM). The SVM yields 100% correct prediction. Although, the gamma operator is worse than SVM, the gamma operator can provide an influence information of inputs to the prediction output. The gamma operator provides that the debt ratio from the 8th previous quarter is the most influential input to the prediction whereas that from the 2nd to 6th previous quarters have small effect to the prediction.

[1]  Min-Yuan Cheng,et al.  Evaluating Contractor Financial Status Using a Hybrid Fuzzy Instance Based Classifier: Case Study in the Construction Industry , 2015, IEEE Transactions on Engineering Management.

[2]  James M. Keller,et al.  Learning the Fuzzy Connectives of a Multilayer Network Using Particle Swarm Optimization , 2007, 2007 IEEE Symposium on Foundations of Computational Intelligence.

[3]  P. Wanke,et al.  Financial distress in electricity distributors from the perspective of Brazilian regulation , 2019, Energy Policy.

[4]  Andrew Lewis,et al.  Grey Wolf Optimizer , 2014, Adv. Eng. Softw..

[5]  Erik Valdemar Cuevas Jiménez,et al.  A swarm optimization algorithm inspired in the behavior of the social-spider , 2013, Expert Syst. Appl..

[6]  Mu-Yen Chen,et al.  Bankruptcy prediction in firms with statistical and intelligent techniques and a comparison of evolutionary computation approaches , 2011, Comput. Math. Appl..

[7]  Xin-She Yang,et al.  Chapter 8 – Firefly Algorithms , 2014 .

[8]  Chao-Ton Su,et al.  Enhanced fuzzy-connective-based hierarchical aggregation network using particle swarm optimization , 2014 .

[9]  Deron Liang,et al.  Financial ratio selection for business crisis prediction , 2011, Expert Syst. Appl..

[10]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[11]  H. Zimmermann,et al.  Decisions and evaluations by hierarchical aggregation of information , 1983 .

[12]  Ali Uyar,et al.  Measuring firm performance using financial ratios: A decision tree approach , 2013, Expert Syst. Appl..

[13]  Chao-Ton Su,et al.  Integrated fuzzy-connective-based aggregation network with real-valued genetic algorithm for quality of life evaluation , 2011, Neural Computing and Applications.

[14]  Hyojoo Son,et al.  Predicting financial distress of contractors in the construction industry using ensemble learning , 2018, Expert Syst. Appl..

[15]  Li Rui,et al.  A particle swarm optimized Fuzzy Neural Network for bankruptcy prediction , 2010, 2010 International Conference on Future Information Technology and Management Engineering.