In order to avoid missing representative features, we should select a lot of features as far as possible when using machine learning algorithms in stock trading. Meanwhile, these high dimensional features can lead to redundancy of information and reduce the efficiency, and accuracy of learning algorithms. It is worth noting that dimensionality reduction operation (DRO) is one of the main means to deal with stock high-dimensional data. However, there are few studies on whether DRO can significantly improve the trading performance of deep neural network (DNN) algorithms. Therefore, this paper selects large-scale stock datasets in the American market and in the Chinese market as the research objects. For each stock, we firstly apply four most widely used DRO, namely principal component analysis (PCA), least absolute shrinkage and selection operator (LASSO), classification and regression trees (CART), and autoencoder (AE) to deal with original features respectively, and then use the new features as inputs of the most six popular DNN algorithms such as Multilayer Perceptron (MLP), Deep Belief Network (DBN), Stacked Auto-Encoders (SAE), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) to generate trading signals. Finally, we apply the trading signals to conduct a lot of daily trading back-testing and non-parameter statistical testing. The experiments show that LASSO can significantly improve the performance of RNN, LSTM, and GRU. In addition, any DRO mentioned in this paper do not significantly improve trading performance and the speed of generating trading signals of the other DNN algorithms.
ParmezanA.R.S.SouzaV.M.A. and BatistaG.E.A.P.A., Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model, Information Science484 (2019), 302–337.
2.
CaiQ.S.ZhangD.F.ZhengW. and LeungC.H., A new fuzzy time series forecasting model combined with ant colony optimization and auto-regression, Knowledge-Based Systems125(1) (2015), 61–68.
3.
ChenA.S.ChangH.C.ChengL.Y, Time-varying Variance Scaling: Application of the Fractionally Integrated ARMA Model, North American Journal of Economics and Finance47 (2019), 1–12.
4.
QinM.J.LiZ.H. and DuZ.H., Red tide time series forecasting by combining ARIMA and deep belief network, Knowledge-Based Systems125 (2017), 39–52.
5.
HungJ.C, A fuzzy GARCH model applied to stock market scenario using a genetic algorithm, Expert Systems with Applications36 (2009), 11710–11717.
6.
DrakosA.A.KouretasG.P. and ZarangasL.P., Forecasting financial volatility of the Athens stock exchange daily returns: An application of the asymmetric normal mixture GARCH model, International Journal of Finance and Economics15(4) (2010), 331–350.
7.
LeeY.S. and TongL.L., Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming, Knowledge-Based Systems24(1) (2011), 66–72.
8.
RounaghiM.M. and ZadehF.N., Investigation of market efficiency and financial stability between S&P500 and London Stock Exchange: monthly and yearly forecasting of time series stock returns using ARMA model, Physica A: Statistical Mechanics and its Applications456(15) (2016), 10–21.
9.
LamC.Y. and LauW.H., A business process activity model and performance measurement using a time series ARIMA intervention analysis, Expert Systems with Application36(3) (2009), 6986–6994.
10.
HenriqueB.M.SobreiroV.A. and KimuraH., Literature review: Machine learning techniques applied to financial market prediction, Expert Systems with Applications124 (2019), 226–151.
11.
HuangW.NakamoriY. and WangS.Y., Forecasting stock market movement direction with support vector machine, Computers & Operations Research32 (2005), 2513–2522.
12.
ChenJ.X., SVM application of financial time series forecasting using empirical technical indicators, In International Conference on Information Networking and Automation1 (2010), 1–77.
13.
XieC.Q., The optimization of share price prediction model based on support vector machine, in: International Conference on Control, Automation and Systems Engineering, 2011, pp. 1–4.
14.
ŁadyżyńskiP.ŻbikowskiK. and GrzegorzewskiP., Stock Trading with Random Forests, Trend Detection Tests and Force Index Volume Indicators, In: International Conference on Artificial Intelligence and Soft Computing, 2013, pp. 441–452.
15.
PatelJ., Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques, Expert Systems with Applications42 (2015), 259–268.
16.
RutaD., Automated Trading with Machine Learning on Big Data, In: 2014 IEEE International Congress on Big Data, 2014, pp. 824–830.
17.
ZbikowskiK., Using Volume Weighted Support Vector Machines with walk forward testing and feature selection for the purpose of creating stock trading strategy, Expert Systems with Application42 (2015), 1797–1805.
18.
DashR. and DashP.K., A hybrid stock trading framework integrating technical analysis with machine learning techniques, The Journal of Finance and Data Science2 (2016), 42–57.
19.
MalagrinoL.S.RomanN.T. and MonteiroA.M., Forecasting stock market index daily direction: A Bayesian Network approach, Expert Systems with Applications105 (2018), 11–22.
20.
BaoW.YueJ. and RaoY.L., A deep learning framework for financial time series using stacked autoencoders and long short term memory, PLoS ONE12(7) (2017), 1–24.
21.
ThomasF. and ChrisstopherK., Deep learning with long short-term memory networks for financial market predictions, Fau Discussion Papers in Economics270(2) (2017), 1–32.
22.
MakickieneN.RutkauskasA.V. and MaknickasA., Investigation of financial market prediction by recurrent neural network, Innovative Info Technologies for Science, Business and Education2(11) (2011), 1–24.
23.
PersioL.D., Recurrent neural networks approach to the financial forecast of Google assets, International Journal of Mathematics and Computers in Simulation11 (2017), 1–7.
24.
DunisC.L.LawsJ. and EvansetB., Trading futures spread portfolios: applications of higher order and recurrent networks, The European Journal of Finance14(6) (2008), 503–521.
25.
ChongE.HanC. and ParkF.C., Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies, Expert Systems with Applications83 (2017), 187–205.
26.
KraussC.DoA. and HucketN., Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P500, European Journal of Operational Research259 (2017), 689–702.
27.
HsiehT.J.HsiaoH. and YehW., Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm, Applied Soft Computing11 (2011), 2510–2525.
28.
LängkvistM.KarlssonL. and LoutfietA., A review of unsupervised feature learning and deep learning for time-series modeling, Pattern Recognition Letters42 (2014), 11–24.
29.
VellaV. and NgW.L., Enhancing risk-adjusted performance of stock market intraday trading with Neuro-Fuzzy systems, Neurocomputing141 (2014), 170–187.
30.
LiuW.B.WangZ.D.LiuX.H.ZengN.Y. and LiuY.R., A survey of deep neural network architectures and their applications, Neurocomputing234 (2017), 11–26.
31.
DixonM., Sequence classification of the limit order book using recurrent neural networks, Journal of Computational Science24 (2018), 277–286.
32.
KimH.Y. and WonC.H., Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type models, Expert Systems with Applications103 (2018), 25–37.
33.
ShenG.Z.TanQ.P.ZhangH.Y.ZengP. and XuJ.J., Deep Learning with Gated Recurrent Unit Networks for Financial Sequence Predictions, Procedia Computer Science131 (2018), 895–903.
34.
SezerO.B.OzbayogluM. and DogduE., A Deep Neural-Network Based Stock Trading System Based on Evolutionary Optimized Technical Analysis Parameters, Procedia Computer Science114 (2017), 473–480.
35.
HuH.P.TangL.ZhangS.H. and WangH.Y., Predicting the direction of stock markets using optimized neural networks with Google Trends, Neurocomputing285 (2018), 188–195.
36.
FischerT. and KraussC., Deep learning with long short-term memory networks for financial market predictions, Fau Discussion Papers in Economics270(2) (2017), 1–32.
37.
HiranshaM.GopalakrishnanE.A.VijayK.M. and SomanK.P., NSE Stock Market Prediction Using Deep-Learning Models, in: International Conference on Computational Intelligence and Data Science, 2018, pp. 1351–1362.
38.
LvD.D.HuangZ.H.LiM.Z. and XiangY., Selection of the optimal trading model for stock investment in different industries, PLoS ONE14(2) (2019), 1–20.
39.
LongW.LuZ.C. and CuiL.X., Deep learning-based feature engineering for stock price movement Prediction, Knowledge-Based Systems164 (2019), 163–173.
40.
HuangC.L. and TsaiC.Y., A hybrid SOFM-SVR with a filter-based feature selection for stock market forecasting, Expert Systems with Applications36 (2009), 1529–1539.
41.
TsaiC.F.HsiaoY.C. and TsaiC.Y., Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches, Decision Support Systems50 (2010), 258–269.
42.
ZhangX.ZHuY.XieK.WangS.Y.NgaiE.W.T. and LiuM., A causal feature selection algorithm for stock prediction modeling, Neurocomputing, 142 (2014), 48–59.
43.
LeeM.C., Using support vector machine with a hybrid feature selection method to the stock trend prediction, Expert Systems with Applications36 (2009), 10896–10904.
44.
SuC.H. and ChengC.H., A hybrid fuzzy time series model based on ANFIS and integrated nonlinear feature selection method for forecasting stock, Neurocomputing205 (2016), 264–273.
45.
NgW.Y.LiangX.L.LiJ.C.YeungD.S. and ChanP.K., LG-Trader: Stock trading decision support based on feature selection by weighted localized generalization error model, Neurocomputing146 (2016), 104–112.
46.
ZhouL.G.SiY.W. and FujitaH., Predicting the listing statuses of Chinese-listed companies using decision trees combined with an improved filter feature selection method, Knowledge-Based Systems128 (2017), 93–101.
47.
ZhongX. and EnkeD., Forecasting daily stock market return using dimensionality reduction, Expert Systems with Applications67 (2017), 126–139.
48.
TayaliH.A. and TolunS., Dimension reduction in mean-variance portfolio optimization, Expert Systems with Applications92 (2018), 161–169.
49.
ChenY.J. and HaoY.J., Integrating principle component analysis and weighted support vector machine for stock trading signals prediction, Neurocomputing321 (2018), 381–402.
50.
NobreJ. and NeversR.F., Combining Principal Component Analysis, Discrete Wavelet Transform and XGBoost to trade in the financial markets, Expert Systems with Applications125 (2019), 181–194.
51.
JamesG.WittenD.HastieT. and TibshiraniR., An Introduction to Statistical Learning with Application in R, in: Heidelberg, Springer, 2009, pp. 228–328..
52.
BourlardH. and KampY., Auto-association by multilayer perceptrons and singular value decomposition, Biological Cybernetics59 (1988), 291–294.
53.
MurphyK.P., Machine Learning: A Probabilistic Perspective, in: Cambridge, Massachusetts, London, The MIT Press, 2012, pp. 563–564.
54.
HintonG.E.OsinderoS. and TheY., A fast learning algorithm for deep belief nets, Neural Computation18 (2006), 1527–1554.
55.
VincentP.LarochelleH.LajoieI.BengioY. and ManzagolP.A., Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion, Journal of Machine Learning Research11 (2010), 3371–3408.
56.
GoodfellowI.BengioY. and CourvilleetY., Deep Learning, in: Cambridge, MA, The MIT Press, 2017, pp. 373–414.
57.
PardoR., The Evaluation and Optimization of Trading Strategies (Second Edition), In: HobokenNJ, John Wiley & Sons: John Wiley & Sons, 2008, pp. 237–261.
58.
AldridgeI., High-Frequency Trading, in: Hoboken, NJ, John Wiley & Sons, 2014, pp. 106–110.
59.
HollanderM. and WolfeD.A., Nonparametric Statistical Methods, in: Hoboken, NJ, John Wiley & Sons, 1973, pp. 115–120.
60.
NemenyiP.B., Distribution-free multiple comparisons, Ph.D. dissertation, State University of New York, 1963.
