Yang, Y., Liu, G., & Zhang, Z. (2000). Stock Market Trend Prediction Based on Neural Networks, Multiresolution Analysis and Dynamical Reconstruction. In Proceedings of the IEEE/IAFE/INFORMS 2000 Conference on Computational Intelligence for Financial Engineering (CIFEr) (pp. 155-156). Institute of Electrical and Electronics Engineers.
https://doi.org/10.1109/CIFER.2000.844615

has been cited by the following article:

• TITLE: How External Trends and Internal Components Decomposition Method Improve the Predictability of Financial Time Series?

  AUTHORS: Fatene Dioubi, Adnan Khurshid

  KEYWORDS: Stock Market, Returns, Predictability, Decomposition Method, Internal Components, Approximate Entropy

  JOURNAL NAME: Journal of Financial Risk Management, Vol.11 No.3, August 30, 2022

  ABSTRACT: Accurately predicting stock market returns can pay off economically not by yielding significant profit but rather by preventing the loss of a large sum of money. Therefore, stocks with a high degree of predictability gain more attention. This study is intended to investigate the impact of decomposing returns on improving predictability. The decomposition method separates the return’s internal components from their external trend. The approximate entropy technique is then applied to quantify their randomness amounts. The results reveal that the decomposition method improved the predictability of returns from S & P 500, Nasdaq 100, SSE and SZSE 500 stocks. Furthermore, the outcomes show that using the return’s absolute value can further enhance its performance. Moreover, this study shows that S & P 500 intraday data are more predictable than their daily data. These findings propose incorporating the decomposition method in the prediction process to improve the predictability and maximise the investor’s profit and minimise their risk.