The stock market is most dominant in today's world in determining the country's economic growth. Accurate price prediction is very necessary and important but faces various difficulties due to the uncertain and fluctuating nature of the stock market. Therefore, a strong prediction model is highly desirable for accurate price prediction. This paper focuses on the effective prediction of the stock market price using historical data and technical indicators. To obtain the desired result this paper proposes a novel multi-layer method. The first layer is based on the Variational Mode Decomposition technique, followed by the Optimized-Kernel Extreme Learning Machine in the second layer and Long Short Term Machine being the final layer. LSTM being less commonly applied in the field of financial market prediction. Hence an attempt has been made in this study for implementing the LSTM for price prediction. The price of different stock markets is used for experimental and validation purposes. Various single-stage methods are used for comparison purposes. The technical indicators along with the historical data are selected as the input variable for prediction purposes. The result analysis shows that the proposed hybrid model performs better than various other techniques mentioned in this study.
BollerslevT. Generalized autoregressive conditional heteroskedasticity. J of Econs1986; 31: 307–327.
2.
RojasIValenzuelaORojasF, et al.Soft-computing techniques and ARMA model for time series prediction. Neurocomputing2008; 71: 519–537.
3.
AwartaniBMCorradiV. Predicting the volatility of the S&P-500 stock index via GARCH models: the role of asymmetries. Int J of Forecasting2005; 21: 167–183.
4.
Kavousi-FardAKhosraviANahavandiS. A new fuzzy-based combined prediction interval for wind power forecasting. IEEE Trans on Power Syst2015; 31: 18–26.
5.
LaboissiereLAFernandesRALageGG. Maximum and minimum stock price forecasting of Brazilian power distribution companies based on artificial neural networks. Appl Soft Comput2015; 35: 66–74.
6.
WengBAhmedMAMegahedFM. Stock market one-day ahead movement prediction using disparate data sources. Expert Syst with Appl2017; 79: 153–163.
7.
LiXXieHWangR, et al.Empirical analysis: stock market prediction via extreme learning machine. Neural Comput Appl2016; 27: 67–78.
8.
TrippiRRTurbanE. Neural networks in finance and investing: using artificial intelligence to improve real world performance. McGraw-Hill, Inc., 1992.
9.
GrigorievskiyAMicheYVenteläAM, et al.Long-term time series prediction using OP-ELM. Neural Netw2014; 51: 50–56.
10.
GuresenEKayakutluGDaimTU. Using artificial neural network models in stock market index prediction. Exp Syst with Appl2011; 38: 10389–10397.
11.
SahinSTolunMRHassanpourR. Hybrid expert systems: a survey of current approaches and applications. Expert Syst with Appl2012; 39: 4609–4617.
12.
MaXJinYDongQ. A generalized dynamic fuzzy neural network based on singular spectrum analysis optimized by brain storm optimization for short-term wind speed forecasting. Appl Soft Comput2017; 54: 296–312.
13.
KristjanpollerWMinutoloMC. Gold price volatility: a forecasting approach using the artificial neural network–GARCH model. Expert Syst with Appl2015; 42: 7245–7251.
14.
YeFZhangLZhangD, et al.A novel forecasting method based on multi-order fuzzy time series and technical analysis. Inf Sci2016; 367: 41–57.
15.
ShukurOBLeeMH. Daily wind speed forecasting through hybrid KF-ANN model based on ARIMA. Renew Energy2015; 76: 637–647.
16.
HeWMengTZhangS, et al.Dual-loop adaptive iterative learning control for a timoshenko beam with output constraint and input backlash. IEEE Trans on Syst, Man, and Cybern: Syst2017; 49: 1027–1038.
17.
HuangGBZhuQYSiewCK.Extreme learning machine: a new learning scheme of feedforward neural networks. In 2004 IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541)2004 July (Vol. 2, pp. 985–990). IEEE.
18.
LiuYLuHYanK, et al.Applying cost-sensitive extreme learning machine and dissimilarity integration to gene expression data classification. Comput Intel Neurosci2016; 1: 8056253.
19.
PalMMaxwellAEWarnerTA. Kernel-based extreme learning machine for remote-sensing image classification. Remote Sens Lett2013; 4: 853–862.
20.
IosifidisATefasAPitasI. DropELM: fast neural network regularization with dropout and DropConnect. Neurocomputing2015; 162: 57–66.
21.
FuHVongCMWongPK,et al.Fast detection of impact location using kernel extreme learning machine. Neural Comput Appl2016; 27: 121–130.
22.
ShamshirbandSMohammadiKChenHL, et al.Daily global solar radiation prediction from air temperatures using kernel extreme learning machine: a case study for Iran. J of Atmosp Solar-Terrestrial Phys2015; 134: 109–117.
23.
ChouJSNguyenTK. Forward forecast of stock price using sliding-window metaheuristic-optimized machine-learning regression. IEEE Trans on Ind Inf2018; 14: 3132–3142.
24.
ChangPCLiuCH. A TSK type fuzzy rule based system for stock price prediction. Expert Syst With Appl2008; 34: 135–144.
25.
ZhangYWuL. Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network. Expert Syst With Appl2009; 36: 8849–8854.
26.
GöçkenMÖzçalıcıMBoruA,et al.Integrating metaheuristics and artificial neural networks for improved stock price prediction. Expert Syst with Appl2016; 44: 320–331.
27.
MajhiRPandaGMajhiB,et al.Efficient prediction of stock market indices using adaptive bacterial foraging optimization (ABFO) and BFO based techniques. Expert Syst with Appl2009; 36: 10097–10104.
28.
MajumderIDashPKBisoiR. Variational mode decomposition based low rank robust kernel extreme learning machine for solar irradiation forecasting. Energy Convers Manage2018; 171: 787–806.
29.
JammaziRAlouiC. Crude oil price forecasting: experimental evidence from wavelet decomposition and neural network modeling. Energy Econ2012; 34: 828–841.
30.
KaoLJChiuCCLuCJ,et al.A hybrid approach by integrating wavelet-based feature extraction with MARS and SVR for stock index forecasting. Decis Supp Syst2013; 54: 1228–1244.
31.
YaslanYBicanB. Empirical mode decomposition based denoising method with support vector regression for time series prediction: a case study for electricity load forecasting. Measurement2017; 103: 52–61.
32.
GuoZZhaoWLuH,et al.Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model. Renew Energy2012; 37: 241–249.
33.
ParasuramanKElshorbagyA.Wavelet networks: an alternative to classical neural networks. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, July. (Vol. 5, pp. 2674–2679). IEEE.
34.
ChangPCWangYWYangWN. An investigation of the hybrid forecasting models for stock price variation in Taiwan. J of the Chinese Instit of Ind Eng2004; 21: 358–368.
35.
MajumderIDashPKBisoiR. Variational mode decomposition based low rank robust kernel extreme learning machine for solar irradiation forecasting. Energy Convers Manage2018; 171: 787–806.
36.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9: 1735–1780.
37.
GersFASchmidhuberJCumminsF. Learning to forget: Continual prediction with LSTM. 1999.
