Stock Market Trend Prediction Using High-Order Information of Time Series
Top Cited Papers
Open Access
- 26 February 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 28299-28308
- https://doi.org/10.1109/access.2019.2901842
Abstract
Given a financial time series such as S&P 500, or any historical data in stock markets, how can we obtain useful information from recent transaction data to predict the ups and downs at the next moment? Recent work on this issue shows initial evidence that machine learning techniques are capable of identifying (non-linear) dependency in the stock market price sequences. However, due to the high volatility and non-stationary nature of the stock market, forecasting the trend of a financial time series remains a big challenge. In this paper, we introduced a new method to simplify noisy-filled financial temporal series via sequence reconstruction by leveraging motifs (frequent patterns), and then utilize a convolutional neural network to capture spatial structure of time series. The experimental results show the efficiency of our proposed method in feature learning and outperformance with 4%-7% accuracy improvement compared with the traditional signal process methods and frequency trading patterns modeling approach with deep learning in stock trend prediction.Funding Information
- National Natural Science Foundation of China (61873218, 61503312)
- Applied Basic Research Foundation of the Sichuan Provincial Science and Technology Department (18YYJC1147)
This publication has 33 references indexed in Scilit:
- Deep learningNature, 2015
- Using Structured Events to Predict Stock Price Movement: An Empirical InvestigationPublished by Association for Computational Linguistics (ACL) ,2014
- Convolutional Neural Networks for Sentence ClassificationPublished by Association for Computational Linguistics (ACL) ,2014
- Exact Discovery of Time Series MotifsPublished by Society for Industrial & Applied Mathematics (SIAM) ,2009
- Superfamily phenomena and motifs of networks induced from time seriesProceedings of the National Academy of Sciences of the United States of America, 2008
- Day-Ahead Electricity Price Forecasting Using the Wavelet Transform and ARIMA ModelsIEEE Transactions on Power Systems, 2005
- Financial time series forecasting using support vector machinesNeurocomputing, 2003
- Application of support vector machines in financial time series forecastingOmega, 2001
- The minimum description length principle in coding and modelingIEEE Transactions on Information Theory, 1998
- Long Short-Term MemoryNeural Computation, 1997