2018/03/13 by Mahsa Ghorbani, Edwin K. P. Chong, Ghorbani, Mahsa +1
Decision Sciences · Economics, Econometrics and Finance · Mathematics · #Artificial intelligence #Complex Systems and Time Series Analysis #Computer science #Covariance #Curse of dimensionality #Dimensionality reduction #Econometrics #FOS: Economics and business #Financial Risk and Volatility Modeling #Mathematical Finance (q-fin.MF) #Mathematics #Principal component analysis #Series (stratigraphy) #Statistic #Statistics #Stock (firearms) #Stock Market Forecasting Methods #Stock price #Subspace topology #Volatility (finance) #q-fin.MF
paper · pdf · doi:10.48550/arxiv.1803.05075
published in arXiv (Cornell University) (Cornell University) · 28 Pages, 10 figures
arxiv created 2018/03/13 · openalex publication_date 2018/03/13 · arxiv updated 2018/03/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The literature provides strong evidence that stock prices can be predicted from past price data. Principal component analysis (PCA) is a widely used mathematical technique for dimensionality reduction and analysis of data by identifying a small number of principal components to explain the variation found in a data set. In this paper, we describe a general method for stock price prediction using covariance information, in terms of a dimension reduction operation based on principle component analysis. Projecting the noisy observation onto a principle subspace leads to a well-conditioned problem. We illustrate our method on daily stock price values for five companies in different industries. 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.