Abstract

Prediction of stock market indices has pinched considerable debate due to its brunt on economic development. Prediction of appropriate stock market indices is important in order to curtail the risk related with it in order to decide on effective investment schemes. Thus, selection of a proper forecasting model is highly appreciated. The objective of this paper is to efficiently normalize data in order to obtain accurate forecasting of stock movement and compare the results. A new technique called the hybrid normalization methodology for the efficient forecasting of stock movement has been implemented. This study discusses three normalization approaches along with our proposed normalization technique and their effect on the forecasting performance. In our work, we implemented Support Vector Machine (SVM), Artificial neural Network (ANN) and K-Nearest Neighbor (KNN) for stock trend forecasting as of their risk management capabilities. This article deals primarily with the normalization of input data for the estimation of stock movement. Simulation was performed on six stock indices (BSESN, NIFTY50, NASDAQ, HANG SENG, NIKKEI225 and SSE composite index) from different parts of the world market. The comparative study indicates that the hybrid normalization process is comparable to other normalization techniques. The results of the hybrid normalization process with ANN are found to be prominent as compared to other classifiers. The approximate accuracy obtained by using the hybrid normalization technique were 71%, 60% and 71% in the combination of KNN, SVM and ANN respectively.

Keyword

Artificial neural network, Hybrid normalization, KNN, SVM, ANN, Stock market indices.

Cite this article

Kumari B, Swarnkar T

Refference

[1][1]Abu-mostafa YS, Atiya AF. Introduction to financial forecasting. Applied Intelligence. 1996; 6(3):205-13.

[2][2]Huang Z, Chen H, Hsu CJ, Chen WH, Wu S. Credit rating analysis with support vector machines and neural networks: a market comparative study. Decision Support Systems. 2004; 37(4):543-58.

[3][3]Fernández-lozano C, Canto C, Gestal M, Andrade-garda JM, Rabuñal JR, Dorado J, et al. Hybrid model based on genetic algorithms and SVM applied to variable selection within fruit juice classification. The Scientific World Journal. 2013.

[4][4]Yeh TL. Capital structure and cost efficiency in the Taiwanese banking industry. The Service Industries Journal. 2011; 31(2):237-49.

[5][5]Vanstone B, Finnie G. An empirical methodology for developing stockmarket trading systems using artificial neural networks. Expert Systems with Applications. 2009; 36(3):6668-80.

[6][6]Jain S, Shukla S, Wadhvani R. Dynamic selection of normalization techniques using data complexity measures. Expert Systems with Applications. 2018; 106:252-62.

[7][7]Khan ZH, Alin TS, Hussain MA. Price prediction of share market using artificial neural network. International Journal of Computer Applications. 2011; 22(2):42-7.

[8][8]Xie B, Passonneau R, Wu L, Creamer GG. Semantic frames to predict stock price movement. In proceedings of the annual meeting of the association for computational linguistics 2013 (pp. 873-83).

[9][9]Chen WH, Shih JY, Wu S. Comparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets. International Journal of Electronic Finance. 2006; 1(1):49-67.

[10][10]García S, Fernández A, Luengo J, Herrera F. Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: experimental analysis of power. Information Sciences. 2010; 180(10):2044-64.

[11][11]Hsu MW, Lessmann S, Sung MC, Ma T, Johnson JE. Bridging the divide in financial market forecasting: machine learners vs. financial economists. Expert Systems with Applications. 2016; 61:215-34.

[12][12]Żbikowski K. Using volume weighted support vector machines with walk forward testing and feature selection for the purpose of creating stock trading strategy. Expert Systems with Applications. 2015; 42(4):1797-805.

[13][13]Tay FE, Cao L. Application of support vector machines in financial time series forecasting. OMEGA. 2001; 29(4):309-17.

[14][14]Sáez JA, Galar M, Luengo J, Herrera F. Tackling the problem of classification with noisy data using multiple classifier systems: analysis of the performance and robustness. Information Sciences. 2013; 247:1-20.

[15][15]Leigh W, Modani N, Hightower R. A computational implementation of stock charting: abrupt volume increase as signal for movement in New York stock exchange composite index. Decision Support Systems. 2004; 37(4):515-30.

[16][16]Racine J. On the nonlinear predictability of stock returns using financial and economic variables. Journal of Business & Economic Statistics. 2001; 19(3):380-2.

[17][17]Mitra SK. Optimal combination of trading rules using neural networks. International Business Research. 2009; 2(1):86-99.

[18][18]Kumari B, Swarnkar T. Importance of data standardization methods on stock indices prediction accuracy. Advanced Computing and Intelligent Engineering. Springer, Berlin. 2020.

[19][19]Kim KJ. Financial time series forecasting using support vector machines. Neurocomputing. 2003; 55(1-2):307-19.

[20][20]Huang W, Nakamori Y, Wang SY. Forecasting stock market movement direction with support vector machine. Computers & Operations Research. 2005; 32(10):2513-22.

[21][21]Barak S, Arjmand A, Ortobelli S. Fusion of multiple diverse predictors in stock market. Information Fusion. 2017; 36:90-102.

[22][22]Dash R, Samal S, Dash R, Rautray R. An integrated TOPSIS crow search based classifier ensemble: in application to stock index price movement prediction. Applied Soft Computing. 2019.

[23][23]Nam K, Seong N. Financial news-based stock movement prediction using causality analysis of influence in the Korean stock market. Decision Support Systems. 2019; 117:100-12.

[24][24]Xu H, Chai L, Luo Z, Li S. Stock movement prediction via gated recurrent unit network based on reinforcement learning with incorporated attention mechanisms. Neurocomputing. 2021; 467(7):214-28.

[25][25]Neely CJ, Rapach DE, Tu J, Zhou G. Forecasting the equity risk premium: the role of technical indicators. Management Science. 2014; 60(7):1772-91.

[26][26]Chen Y, Hao Y. A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction. Expert Systems with Applications. 2017; 80:340-55.

[27][27]Jha P, Mohan N, Laha AK, Dutta G. Artificial neural network models for forcasting stock price index in Bombay stock exchange. IIMA Institutional Repository. 2010.

[28][28]Altay E, Satman MH. Stock market forecasting: artificial neural network and linear regression comparison in an emerging market. Journal of Financial Management & Analysis. 2005; 18(2):18-33.

[29][29]Han H, Men K. How does normalization impact RNA-seq disease diagnosis?. Journal of Biomedical Informatics. 2018; 85:80-92.

[30][30]Garcia LP, De CAC, Lorena AC. Effect of label noise in the complexity of classification problems. Neurocomputing. 2015; 160:108-19.

[31][31]Sahin U, Ozbayoglu AM. TN-RSI: Trend-normalized RSI indicator for stock trading systems with evolutionary computation. Procedia Computer Science. 2014; 36:240-5.

[32][32]Cao LJ, Tay FE. Support vector machine with adaptive parameters in financial time series forecasting. IEEE Transactions on Neural Networks. 2003; 14(6):1506-18.

[33][33]Senol D, Ozturan M. Stock price direction prediction using artificial neural network approach: the case of Turkey. Journal of Artificial Intelligence. 2009; 1(2):70-7.

[34][34]Kaastra I, Boyd M. Designing a neural network for forecasting financial and economic time series. Neurocomputing. 1996; 10(3):215-36.

[35][35]Vanstone BJ, Finnie GR. Combining technical analysis and neural networks in the Australian stockmarket. In international conference on artificial intelligence and soft computing 2006 (pp. 125-30).