A modular Takagi-Sugeno-Kang (TSK) system based on a modified hybrid soft clustering for stock selection

Document Type : Article

Authors

1 Department of Industrial Engineering, Meybod University, Meybod, Iran

2 Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, P.O. Box 15914, Iran

Abstract

This study presents a new hybrid intelligent system with ensemble learning for stock selection using the fundamental information of companies. The system uses the selected financial ratios of each company as the input variables and ranks the candidate stocks. Due to the different characteristics of the companies from different activity sectors, modular system for stock selection may show a better performance in comparison with an individual system. Here, a hybrid soft clustering algorithm is proposed to eliminate the noise and partition the input data set into more homogeneous overlapped subsets. The proposed clustering algorithm benefits from the strengths of the fuzzy, possibilistic and rough clustering to develop a modular system. An individual Takagi-Sugeno-Kang (TSK) system is extracted from each subset using an artificial neural network and genetic algorithm. To integrate the outputs of the individual TSK systems, a new weighted ensemble strategy is proposed. The performance of the proposed system is evaluated among 150 companies listed on Tehran Stock Exchange (TSE) regarding information coefficient, classification accuracy and appreciation in stock price. The experimental results show that the proposed modular TSK system significantly outperforms the single TSK system as well as the other ensemble models using different decomposition and combination strategies.

Keywords


  1. References:

    1. Edirisinghe, N. C. P. and Zhang, X., “Generalized DEA model of fundamental analysis and its applications to portfolio optimization”. Journal of Banking & Finance, 31(11), pp. 3311–3335 (2007).
    2. Liu, H., Mulvey, J., and Zhao, T., “A semiparametric graphical modelling approach for large-scale equity selection”. Quantitative Finance, 16(7), pp. 1053–1067 (2016).
    3. Quah, T. S., “DJIA stock selection assisted by neural network”. Expert Systems with Applications, 35, pp. 50–58 (2008).
    4. Chen, Y. S. and Cheng, C. H., “Evaluating industry performance using extracted RGR rules based on feature selection and rough sets classifier”. Expert Systems with Applications, 36, pp. 9448–9456 (2009).
    5. Esfahanipour, A. and Mousavi, S., “A genetic programming model to generate risk-adjusted technical trading rules in stock markets”. Expert Systems with Applications, 38(7), 8438-8445 (2011).
    6. Mousavi, S., Esfahanipour, A. and Fazel Zarandi, M. H., “A Novel Approach to Dynamic Portfolio Trading System Using Multitree Genetic Programming”. Knowledge-Based Systems, 66, 68-81 (2014).
    7. Shen, R.K., Yang, C. Y., Shen, V.R.L., Li, W.C. and Chen, T.S., “A Stock Market Prediction System Based on High-Level Fuzzy Petri Nets”. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 26(5), 771-808 (2018).
    8. Yunusoglu, M. G. and Selim, H., “A fuzzy rule based expert system for stock evaluation and portfolio construction: An application to Istanbul Stock Exchange”. Expert Systems with Applications, 40, 908–920 (2013).
    9. Reilly, F. K. and Brown, K. C., Investment analysis and portfolio management, 7th ed., South-Western College Publications, (2004).
    10. Haykin, S., Neural Networks, A comprehensive foundation, Chapter. 7, pp. 351- 391, Prentice Hall Inc., New Jersey (1999).
    11. Kumar, R. S. and Arasu, G. T., “Rough Set Theory and Fuzzy Logic Based Warehousing of Heterogeneous Clinical Databases”. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 25(3), 385-408 (2017).
    12. Finlay, S., “Multiple classifier architectures and their application to credit risk assessment”. European Journal of Operational Research, 210, 368–378 (2011).
    13. Melin, P., Sánchez, D. and Castillo, O., “Genetic optimization of modular neural networks with fuzzy response integration for human recognition”. Information Sciences, 197, 1–19 (2012).
    14. Kuncheva, L. I., “Switching between selection and fusion in combining classifiers: an experiment”. IEEE Transactions on Systems, Man and Cybernetics - Part B: Cybernetics, 32, 146–156 (2002).
    15. Lim, M. K. and Sohn, S. Y., “Cluster-based dynamic scoring model”. Expert Systems with Applications, 32, 427–431 (2007).
    16. Shahrabi, J., Hadavandi, E. and Asadi, S., “Developing a hybrid intelligent model for forecasting problems: Case study of tourism demand time series”. Knowledge-Based Systems, 43, 112–122 (2013).
    17. Alikhani, M., Nedaie, A. and Ahmadvand, A., “Presentation of clustering-classification heuristic method for improvement accuracy in classification of severity of road accidents in Iran”. Safety Science, 60, 142–150 (2013).
    18. Maji, P. and Pal, S. K., “Rough set based generalized fuzzy C-means algorithm and quantitative indices”. IEEE Trans. Syst. Man Cybern. B: Cybern., 37 (6), 1529–1540 (2007).
    19. Lingras, P., Nimse, S., Darkunde, N. and Muley, A., “Soft Clustering from Crisp Clustering using Granulation for Mobile Call Mining”. IEEE International Conference on Granular Computing (GrC), (2011).
    20. Liu, Y. H., Lin, S. H., Hsueh, Y. L. and Lee, M. J., “Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble”. Expert Systems with Applications, 36, 1978–1998 (2009).
    21. Lingras, P. and West, C., “Interval set clustering of web users with rough k-means”. Tech. Rep. 2002-002, Department of Mathematics and Computer Science, St. Mary’s University, Halifax, Canada (2002).
    22. Mitra, S., Banka, H. and Pedrycz, W., “Rough-fuzzy collaborative clustering”. IEEE Transactions on Systems, Man, and Cybernetics – Part B: Cybernetics, 36 (4), 795–805 (2006).
    23. Peters, G., Crespo, F., Lingras, P. and Weber, R., “Soft clustering - fuzzy and rough approaches and their extensions and derivatives”. International Journal of Approximate Reasoning, 54, 307–322 (2013).
    24. Maji, P. and Pal, S. K., “RFCM: A hybrid clustering algorithm using rough and fuzzy sets”. Fundamenta Informaticae, 80(4), 475–496 (2007).
    25. Hu, J., Li, T., Luo, C., Fujita, H. and Yang, Y., “Incremental fuzzy cluster ensemble learning based on rough set theory”. Knowledge-Based Systems, 132, 144-155 (2017).
    26. Mitra, S. and Barman, B., “Rough-Fuzzy Clustering: An Application to Medical Imagery”. in Rough Sets and Knowledge Technology, RSKT 2008. Lecture Notes in Computer Science, vol. 5009, eds. Wang G., Li T., Grzymala-Busse J.W., Miao D., Skowron A. and Yao Y., pp. 300-307, Springer, Berlin, Heidelberg (2008).
    27. Maji, P. and Pal, S. K., Rough-Fuzzy Pattern Recognition: Applications in Bioinformatics and Medical Imaging, Wiley-IEEE Press (2012).
    28. Maji, P. and Roy, S., “Rough-fuzzy clustering and multiresolution image analysis for text-graphics segmentation”. Applied Soft Computing, 30, 705–721 (2015).
    29. Saha, I., Sarkar, J. P. and Maulik, U., “Ensemble based rough fuzzy clustering for categorical data”. Knowledge-Based Systems, 77, 114-127 (2015).
    30. Saha, I., Sarkar, J. P. and Maulik, U., “Integrated Rough Fuzzy Clustering for Categorical data Analysis”. Fuzzy Sets and Systems, 361, pp. 1-32 (2019).
    31. Chandra, A. and Yao, X., “Evolving hybrid ensembles of learning machines for better generalization”. Neurocomputing, 69, 686-700 (2006).
    32. Rodriguez, J. J, Kuncheva, L. I., Alonso, C. J., “Rotation forest: A new classifier ensemble method”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28, 1619-1630 (2006).
    33. Masnadi-Shirazi, H. and Vasconcelos, N., “Cost-sensitive boosting”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 294-309 (2011).
    34. Abdullah, M. and Ganapathy, V., “Neural network ensemble for financial trend prediction”. In TENCON Proceedings IEEE, 157–161 (2000).
    35. Chun, S. H. and Park, Y. J., “Dynamic adaptive ensemble case-based reasoning: Application to stock market prediction”. Expert Systems with Applications, 28, 435–443 (2005).
    36. Chen, Y., Yang, B., Abraham, A., “Flexible neural trees ensemble for stock index modeling”. Neurocomputing, 70, 697–703 (2007).
    37. Creamer, G. and Freund, Y., “Automated trading with boosting and expert weighting”. Quantitative Finance, 4, 401–420 (2010).
    38. Tsai, C. F., Lin, Y. C., Yen, D. C. and Chen, Y. M., “Predicting stock returns by classifier ensembles”. Applied Soft Computing, 11, 2452–2459 (2011).
    39. Xiao, Y., Xiao, J., Lu, F. and Wang, S., “Ensemble ANNs-PSO-GA approach for day a head stock e-exchange prices forecasting”. International Journal of Computational Intelligence Systems, 6, 96–114 (2013).
    40. Booth, A., Gerding, E. and McGroarty, F., “Automated trading with performance weighted random forests and seasonality”. Expert Systems with Applications, 41, 3651–3661 (2014).
    41. Pulido, M., Melin, P. and Castillo, O., “Particle swarm optimization of ensemble neural networks with fuzzy aggregation for time series prediction of the Mexican Stock Exchange”. Information Sciences, 280, 188-204 (2014).
    42. Suzuki, T. and Ohkura, Y., “Financial technical indicator based on chaotic bagging predictors for adaptive stock selection in Japanese and American markets”. Physica A: Statistical Mechanics and its Applications, 442, 50–66 (2016).
    43. Holopainen, M. and Sarlin, P., “Toward robust early-warning models: a horse race, ensembles and model uncertainty”. Quantitative Finance, 17(12), 1933-1963 (2017).
    44. Kuncheva, L. I., Bezdek, J. C. and Duin, R. P. W., “Decision templates for multiple classifier fusion: an experimental comparison”. Pattern Recognition, 34, 299–314 (2001).
    45. Kuncheva, L. I., Combining Pattern Classifiers, Methods and Algorithms. Wiley, Hoboken, New Jersey (2004).
    46. Zhou, L., Lai, K. K. and Yu, L., “Least squares support vector machines ensemble models for credit scoring”.  Expert Systems with Applications, 37, 127-133 (2010).
    47. Gheyas, I. A. and Smith, L. S., “A novel neural network ensemble architecture for time series forecasting”. Neurocomputing, 74(18), 3855-3864 (2011).
    48. Lv, Y., Liu, J., Yang, T. and Zeng, T., “A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler”, Energy, 55, 319-329 (2013).
    49. Liu, Y., Li, C. and Gao, Z., “A novel unified correlation model using ensemble support vector regression for prediction of flooding velocity in randomly packed towers”. Journal of Industrial and Engineering Chemistry, 20, 1109–1118 (2014).
    50. Albadvi, S., Chaharsooghi, K. and Esfahanipour, A., “Decision making in stock trading: An application of PROMETHEE”. European Journal of Operational Research, 177, 673–683 (2007).
    51. Shen, K. Y., Yan, M. R. and Tzeng, G. H., “Combining VIKOR-DANP model for glamor stock selection and stock performance improvement”. Knowledge-Based Systems, 58, 86–97 (2014).
    52. Eckbo, B. E., Makaew, T., Thorburn, K. S., “Are stock-financed takeovers opportunistic?”. Journal of Financial Economics, 128(3), 443-465 (2018).
    53. Zhang, H. and Yan, C., “Modelling fundamental analysis in portfolio selection”. Quantitative Finance, 18(8), 1315-1326 (2018).
    54. Chen, Y. S. and Cheng, C. H., “Forecasting PGR of the financial industry using a rough sets classifier based on attribute-granularity”. Knowledge and Information Systems, 25, 57–79 (2010).
    55. Esfahanipour, A., Goodarzi, M. and Jahanbin, R., “Analysis and forecasting of IPO underpricing”. Neural Computing and Applications, 27, 651–658 (2016).
    56. Tan, Z., Yan, Z., Zhu, G., “Stock selection with random forest: An exploitation of excess return in the Chinese stock market”. Heliyon, 5 (8), (2019).
    57. Yang, F., Chen, Z., Li, J., Tang, L., “A novel hybrid stock selection method with stock prediction”, Applied Soft Computing, 80, pp. 820-831 (2019).
    58. Babazadeh, H., Esfahanipour, A. “A novel multi period mean-VaR portfolio optimization model considering practical constraints and transaction cost”, Journal of Computational and Applied Mathematics, 361, pp. 313-342 (2019).
    59. Vanstone, B., Finnie, G. and Hahn, T., “Creating trading systems with fundamental variables and neural networks: The Aby case study”. Mathematics and Computers in Simulation, 86, 78–91 (2012).
    60. Becker, L. Y., Fei, P. and Lester, A. M., “Stock Selection – An Innovative Application of Genetic Programming Methodology”, In Genetic Programming Theory and Practice IV, edited by R. Riolo, T. Soule, B. Worzel, pp. 315-334, Springer-Verlag, US (2007).
    61. Parque, V., Mabu, S. and Hirasawa, K., “Evolving Asset Selection using Genetic Network Programming”. IEEJ transactions on electrical and electronic engineering, 7, 174–182 (2012).
    62. Ince, H., “Short term stock selection with case-based reasoning technique”. Applied Soft Computing, 22, 205–212 (2014).
    63. Silva, A., Neves, R. and Horta, N., “A Hybrid Approach to Portfolio Composition based on Fundamental and Technical Indicators”. Expert Systems with Applications, 42 (4), 2036-2048 (2015).
    64. Yu, H., Chen, R. and Zhang, G., “A SVM Stock Selection Model within PCA”. Procedia Computer Science, 31, 406-412 (2014).
    65. Huang C. F., Chang C. H., Chang B. R. and Cheng D. W., “A Study of a Hybrid Evolutionary Fuzzy Model for Stock Selection”. IEEE International Conference on Fuzzy Systems, Taipei, Taiwan (2011).
    66. Shen, K. Y. and Tzeng, G. H., “Combined soft computing model for value stock selection based on fundamental analysis”. Applied Soft Computing, 37, 142–155 (2015).
    67. Sang, X., Zhou, Y., Yu, X., “An uncertain possibility-probability information fusion method under interval type-2 fuzzy environment and its application in stock selection”, Information Sciences, 504, pp. 546-560 (2019).
    68. ThakurS.M., Bhattacharyya, R., Sarkar, S., “Stock portfolio selection using Dempster–Shafer evidence theory”, Journal of King Saud University - Computer and Information Sciences, 30 (2), pp. 223-235 (2018).
    69. Chang, P. C. and Liu, C. H., “A TSK type fuzzy rule based system for stock price prediction”. Expert systems with Applications, 34(1), 135-144 (2008).
    70. Esfahanipour, A. and Aghamiri, W., “Adapted neuro-fuzzy inference system on indirect approach TSK fuzzy rule base for stock market analysis”. Expert systems with Applications, 37(7), 4742-4748 (2010).
    71. Mousavi, S., Esfahanipour, A. and Fazel Zarandi, M. H., “MGP-INTACTSKY: Multitree Genetic Programming-based learning of INTerpertable and Accurate TSK sYstems for dynamic portfolio trading”. Applied soft computing, 34, 449- 462 (2015).
    72. Pawlak, Z. Rough Sets: Theoretical Aspects of Reasoning About Data. Springer, Netherlands (1991).
    73. Sarkar, J. P., Saha, I. and Maulik, U., “Rough Possibilistic  Type-2  Fuzzy  C-Means  clustering  for  MR  brain image  segmentation”. Applied  Soft  Computing, 46, 527–536 (2016).
    74. Zhang, T., Chen, L., and Ma, F., “A modified rough c-means clustering algorithm based on hybrid imbalanced measure of distance and density”. International Journal of Approximate Reasoning, 55(8), 1805-1818 (2014).
    75. Melek, W. W., Goldenberg, A. A. and Emami, M. R., “A fuzzy noise-rejection data partitioning algorithm”. International Journal of Approximate Reasoning, 38, 1–17 (2005).
    76. Emami, M. R., Turksen, I. B. and Goldenberg, A. A., “Development of a systematic methodology of fuzzy logic modeling”. IEEE Transactions on Fuzzy Systems, 6(3), 346–361 (1998).
    77. Krishnapuram, R. and Keller, J. M., “A Possibilistic Approach to Clustering”. Fuzzy Systems, IEEE Transactions on, 1(2), 98 - 110 (1993).
    78. Fazel Zarandi, M. H., Doostparast Torshizi, A., Turksen, I. B. and Rezaee, B., “A new indirect approach to the type-2 fuzzy systems modeling and design”. Information Sciences, 232, 346-365 (2013).
    79. Hadavandi, E., Shavandi, H. and Ghanbari, A., “Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting”. Knowledge-Based Systems, 23(8), 800-808 (2010).
    80. Park, B. J., Kim, W. D., Oh, S. K. and Pedrycz, W., “Fuzzy set-oriented neural networks based on fuzzy polynomial inference and dynamic genetic optimization”. Knowledge and Information Systems, 39, 207–240 (2014).
    81. Adeli, H. and Hung, S. L., Machine learning: neural networks, genetic algorithms, and fuzzy systems, John Wiley & Sons, New York (1994).
    82. Karray, F. O. and De Silva, C. W., Soft computing and intelligent systems design: theory, tools, and applications, Addison-Wesley, Boston (2004).
    83. Alcal´a, R., Ducange, P., Herrera, F., Lazzerini, B. and Marcelloni, F., “A multiobjective evolutionary approach to concurrently learn rule and data bases of linguistic fuzzy-rule-based systems”. Fuzzy Systems, IEEE Transactions on, 17(5), 1106-1122 (2009).
    84. Casillas, J. and Carse, B., “Special issue on Genetic Fuzzy Systems: Recent Developments and Future Directions”. Soft Computing, 13(5), 417-418 (2009).
    85. Ishibuchi, H. and Nojima, Y., “Analysis of interpretability-accuracy tradeoff of fuzzy systems by multiobjective fuzzy genetics-based machine learning”. International Journal of Approximate Reasoning, 44(1), 4-31 (2007).
    86. Herrera, F., “Genetic fuzzy systems: taxonomy, current research trends and prospects”. Evolutionary Intelligence, 1(1), 27-46 (2008).
    87. Verikas, A., Guzaitis, J., Gelzinis, A. and Bacauskiene, M., “A general framework for designing a fuzzy rule-based classifier”. Knowledge and Information Systems, 29, 203–221 (2011).
    88. McGee, R., O’Neill, M. and Brabazon, A., “The Syntax of Stock Selection: Grammatical Evolution of a Stock Picking Model”. IEEE Congress on Evolutionary Computation (CEC), 1-8 (2010).
    89. TSETMC: Tehran Securities Exchange Technology Management Co., Available online at: http://irbourse.com/NewsTag.aspx?tag=50, (accessed 15 June 2017).
    90. Barak, S. and Modarres, M., “Developing an approach to evaluate stocks by forecasting effective features with data mining methods”. Expert Systems with Applications, 42, 1325–1339 (2015).
    91. Ghandar, A., Michalewicz, Z., Schmidt, M., Tô, T. D. and Zurbrugg, R., “Computational intelligence for evolving trading rules”. IEEE Transactions on Evolutionary Computation, 13(1), 71-86 (2009).
    92. Gillam, R. A., Guerard, J. B. and Cahan, R., “News volume information: Beyond earnings forecasting in a global stock selection model”. International Journal of Forecasting, 31(2), 575-581 (2015).
    93. Guerard, J. B., Markowitz, H. and Xu, G., “Earnings forecasting in a global stock selection model and efficient portfolio construction and management”. International Journal of Forecasting, 31(2), 550-560 (2015).
    94. Kroll, B., Trichilo, D. and Braun, J., Extending the fundamental law of investment management, JPMorgan asset management, 2005, available online at: https://www.jpmorgan.com/cm/BlobServer/Extending_the_Fundamental_Law_of_Investment_Management_.pdf?blobkey=id&blobwhere=1158630145176&blobheader=application%2Fpdf&blobheadername1=Cache-Control&blobheadervalue1=private&blobcol=urldata&blobtable=MungoBlobs.
    95. Huang, C. F., “A hybrid  stock  selection  model  using  genetic  algorithms  and  support  vector regression”. Applied  Soft  Computing, 12, 807–818 (2012).