Development of Intelligent Stock Trading System Using Pattern Independent Predictor and Turning Point Matrix

Yoojeong Song (), Jae Won Lee () and Jongwoo Lee ()
Additional contact information
Yoojeong Song: Sookmyung Women’s University
Jae Won Lee: Sungshin Women’s University
Jongwoo Lee: Sookmyung Women’s University

Computational Economics, 2022, vol. 59, issue 1, No 2, 27-38

Abstract: Abstract In this paper, we propose an intelligent stock trading system utilizing moving average patterns which reflect short-term fluctuations in stock price and turning point matrix which represents the long term stock price fluctuation. The core technique of our intelligent stock trading system are as follows. The first technique is the composition of pattern-intensive data based on the fluctuation pattern of the moving average line. We constructed pattern-specific predictors for each of the four patterns using the golden cross, the rising transition point and arrangement of the moving average lines. The four specific patterns we defined were developed based on the analysis method commonly used in stock chart analysis. This pattern specific predictors makes it possible to construct pattern-intensive data, and we proved that the pattern-intensive data can improve the performance of the stock price prediction model through experiments. Our second core technique is the Fibonacci sequence-based turning point matrix. Using this, the process of long-term stock price fluctuations can be expressed in a compact way. We used a combination of pattern-specific predictors and turning point matrix to construct input features that could reflect the pattern of constant fluctuations in stock prices in the short and long term. Finally, we have developed a stock trading system that uses this input features to predict future price changes and obtain profit above market returns

Keywords: Deep learning; Stock price prediction; Moving average; Pattern specific predictor; Turning point matrix (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10614-020-10066-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:compec:v:59:y:2022:i:1:d:10.1007_s10614-020-10066-6

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-020-10066-6

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().