Abstract
In this study, we attempt to discover and predict stock index patterns through analysis of multivariate time series. Our motivation is based on the notion that financial planning guided by pattern discovery and prediction of stock index prices maybe more realistic and effective than traditional approaches, such as Autoregressive Integrated Moving Average (ARIMA) model. A three-stage architecture constructed by combining Toeplitz Inverse Covariance-Based Clustering (TICC), Temporal Pattern Attention and Long- Short-Term Memory (TPA-LSTM) and Multivariate LSTM-FCNs (MLSTM-FCN and MALSTM-FCN) is applied for pattern discovery and prediction of stock index. In the first stage, we use TICC to discover repeated patterns of stock index. Then, in the second stage, TPA-LSTM that considers weak periodic patterns and long short-term information is used to predict multivariate stock indices. Finally, in the third stage, MALSTM-FCN is applied to predict stock index price pattern. The Hangseng Stock Index and eleven industrial sub-indices are used in the experiment. Empirical results show that the three-stage architecture achieves satisfactory and better performance than traditional methods, such as Naive Bayes Classifier (NB), Support Vector Machine Classifier (SVM), Random Forest (RF), etc. Moreover, we construct equal proportion portfolios based on the bullish trading rules to further analyze the feasibility of the proposed three-stage architecture. Seven comprehensive stock indices are used in the experiment. Empirical results show that the portfolio based on the proposed three-stage architecture presents better performance than the market-based portfolio. These findings may provide new direction for the portfolio construction and risk aversion.
Highlights
Stock index prediction is one of the most important subjects in financial time series forecasting
This paper proposes a three-stage architecture that consists of Toeplitz Inverse Covariance-Based Clustering (TICC), TPA-long short-term memory network (LSTM), Multivariate LSTM-Fully Convolutional Network (FCN) to discover and predict repeated patterns of stock index
This paper makes up for the shortcomings of previous research, which forms a complete structure of stock index pattern discovery and prediction through a proposed threestage architecture of TICC, TPA-LSTM, and Multivariate LSTM-FCNs
Summary
Stock index prediction is one of the most important subjects in financial time series forecasting. Stock index characteristics, including ‘‘noisy’’ and ‘‘non-stationary’’, make prediction face challenges. ‘Nonstationary’ means that stock index may change dramatically in different periods. These characteristics lead to poor stock index prediction results as predicted by traditional econometric models such as linear model, Auto-Regressive Integrated Moving Average (ARIMA), and Vector AutoRegression (VAR) [1]–[3]. The aforementioned methods belong to short-term predictions in time series, which are seriously affected by ‘‘noisy’’ and ‘‘non-stationary’’. If stock index prediction only focuses on forecasting the trend over a certain period, the effects of ‘‘noisy’’ and ‘‘non-stationary’’ on the prediction results will be eliminated. One of methods of stock index trend prediction over a certain period is to decompose stock
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
