Stock price prediction using principal components

The literature provides strong evidence that stock price values can be predicted from past price data. Principal component analysis (PCA) identifies a small number of principle components that explain most of the variation in a data set. This method is often used for dimensionality reduction and analysis of the data. In this paper, we develop a general method for stock price prediction using time-varying covariance information. To address the time-varying nature of financial time series, we assign exponential weights to the price data so that recent data points are weighted more heavily. Our proposed method involves a dimension-reduction operation constructed based on principle components. Projecting the noisy observation onto a principle subspace results in a well-conditioned problem. We illustrate our results based on historical daily price data for 150 companies from different market-capitalization categories. We compare the performance of our method to two other methods: Gauss-Bayes, which is numerically demanding, and moving average, a simple method often used by technical traders and researchers. We investigate the results based on mean squared error and directional change statistic of prediction, as measures of performance, and volatility of prediction as a measure of risk.

[1]  Charles Trzcinka,et al.  Sequential Tests of the Arbitrage Pricing Theory: A Comparison of Principal Components and Maximum Likelihood Factors , 1990 .

[2]  Jong Won Park,et al.  Effects of common factors on stock correlation networks and portfolio diversification , 2017 .

[3]  Rongda Chen,et al.  A SVM Stock Selection Model within PCA , 2014, ITQM.

[4]  K. French,et al.  Stock return variances: The arrival of information and the reaction of traders , 1986 .

[5]  T. Ando,et al.  Stock return predictability: A factor-augmented predictive regression system with shrinkage method , 2018 .

[6]  Hugo Van hamme,et al.  A Review of Signal Subspace Speech Enhancement and Its Application to Noise Robust Speech Recognition , 2007, EURASIP J. Adv. Signal Process..

[7]  Impact of financial market uncertainty and macroeconomic factors on stock–bond correlation in emerging markets , 2016 .

[8]  Michel Ballings,et al.  Evaluating multiple classifiers for stock price direction prediction , 2015, Expert Syst. Appl..

[9]  Anders Lindquist,et al.  On the Nonlinear Dynamics of Fast Filtering Algorithms , 1994 .

[10]  Wenjun Xue,et al.  Stock Return Autocorrelations and Predictability in the Chinese Stock Market: Evidence from Threshold Quantile Autoregressive Models , 2017 .

[11]  M. Sadique,et al.  Behaviour of Stock Return Autocorrelation in the GCC Stock Markets , 2015 .

[12]  Robert R. Meglen,et al.  Examining large databases: A chemometric approach using principal component analysis , 1991 .

[13]  M. Potters,et al.  Exponential Weighting and Random-Matrix-Theory-Based Filtering of Financial Covariance Matrices for Portfolio Optimization , 2004, cond-mat/0402573.

[14]  J. Lewellen.  The Cross Section of Expected Stock Returns , 2014 .

[15]  Josef Lakonishok,et al.  Performance measurement methodology and the question of whether stocks overreact / 1991:130 , 1991 .

[16]  Stewart Mayhew,et al.  Stock Returns, Implied Volatility Innovations, and the Asymmetric Volatility Phenomenon , 2006, Journal of Financial and Quantitative Analysis.

[17]  P. Narayan,et al.  Can institutions and macroeconomic factors predict stock returns in emerging markets , 2014 .

[18]  Jun Wang,et al.  Forecasting stock market indexes using principle component analysis and stochastic time effective neural networks , 2015, Neurocomputing.

[19]  B. LeBaron,et al.  Simple Technical Trading Rules and the Stochastic Properties of Stock Returns , 1992 .

[20]  T.B. Trafalis,et al.  Kernel principal component analysis and support vector machines for stock price prediction , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[21]  Jonathan Rougier,et al.  Ensemble Averaging and Mean Squared Error , 2016 .

[22]  M. Sadique,et al.  Stock return autocorrelation, day of the week and volatility: An empirical investigation on the Saudi Arabian stock market , 2017 .

[23]  Ali N. Akansu,et al.  Portfolio Risk in Multiple Frequencies , 2011, IEEE Signal Processing Magazine.

[24]  E. Fama,et al.  Dividend yields and expected stock returns , 1988 .

[25]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[26]  Infrequent Rebalancing, Return Autocorrelation, and Seasonality , 2015 .

[27]  Maciej Augustyniak.  Maximum Likelihood Estimation of the Markov-Switching GARCH Model , 2014, Comput. Stat. Data Anal..

[28]  Fiona Steele,et al.  Analysis of Multivariate Social Science Data , 2008 .

[29]  C. Alexander,et al.  Market risk analysis IV: value-at-risk models , 2008 .

[30]  Xiao Zhong,et al.  Forecasting daily stock market return using dimensionality reduction , 2017, Expert Syst. Appl..

[31]  Tim Futing Liao,et al.  Analysis of Multivariate Social Science Data , 2010 .

[32]  A. Lo,et al.  Stock Market Prices Do Not Follow Random Walks: Evidence from a Simple Specification Test , 1987 .

[33]  E. Fama,et al.  Permanent and Temporary Components of Stock Prices , 1988, Journal of Political Economy.

[34]  Vincent Bogousslavsky.  Infrequent Rebalancing, Return Autocorrelation, and Seasonality: Infrequent Rebalancing, Return Autocorrelation, and Seasonality , 2016 .

[35]  Mark P. Taylor,et al.  The use of technical analysis in the foreign exchange market , 1992 .

[36]  Matthew R. McKay,et al.  Minimum variance portfolio optimization with robust shrinkage covariance estimation , 2014, 2014 48th Asilomar Conference on Signals, Systems and Computers.

[37]  Phillipp Meister,et al.  Statistical Signal Processing Detection Estimation And Time Series Analysis , 2016 .

[38]  Stephen E. Satchell,et al.  Time series momentum trading strategy and autocorrelation amplification , 2015 .

[39]  G. Pasini.  PRINCIPAL COMPONENT ANALYSIS FOR STOCK PORTFOLIO MANAGEMENT , 2017 .

[40]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[41]  J. Wilder.  New Concepts in Technical Trading Systems , 1978 .

[42]  W F Velicer,et al.  Component Analysis versus Common Factor Analysis: Some issues in Selecting an Appropriate Procedure. , 1990, Multivariate behavioral research.

[43]  Liyan Han,et al.  The effect of oil returns on the stock markets network , 2019, Physica A: Statistical Mechanics and its Applications.

[44]  Jun Yang,et al.  Stock Market Autoregressive Dynamics: A Multinational Comparative Study with Quantile Regression , 2016 .

[45]  A. Craig MacKinlay,et al.  Stock Market Prices Do Not Follow Random Walks: Evidence from a Simple Specification Test , 1988 .

[46]  T. Teräsvirta,et al.  Multivariate Autoregressive Conditional Heteroskedasticity with Smooth Transitions in Conditional Correlations , 2005 .

[47]  Donald B. Keim,et al.  Earnings Yields, Market Values, and Stock Returns , 1989 .

[48]  W. Fung,et al.  Empirical Characteristics of Dynamic Trading Strategies: The Case of Hedge Funds , 1997 .

[49]  Olivier Ledoit,et al.  Improved estimation of the covariance matrix of stock returns with an application to portfolio selection , 2003 .

[50]  Jingtao Yao,et al.  A case study on using neural networks to perform technical forecasting of forex , 2000, Neurocomputing.

[51]  P. Seiler,et al.  Speculative dynamics , 2010 .

[52]  R. Thaler,et al.  Does the Stock Market Overreact , 1985 .

[53]  R. Kumaresan,et al.  Data adaptive signal estimation by singular value decomposition of a data matrix , 1982, Proceedings of the IEEE.

[54]  Olivier Ledoit,et al.  A well-conditioned estimator for large-dimensional covariance matrices , 2004 .