Home // ALLDATA 2018, The Fourth International Conference on Big Data, Small Data, Linked Data and Open Data // View article

Design and Implementation of Candlestick Chart Retrieval Algorithm for Predicting Stock Price Trend

Authors:
Yoshihisa Udagawa

Keywords: Stock price prediction; Technical analysis; Candlestick charts; Longest common subsequence algorithm for numbers; Multi numerical attributes; Nikkei stock average;

Abstract:
Advances in data mining techniques are now making it possible to analyze a large amount of stock data for predicting future price trends. The candlestick charting is one of the most popular techniques used to predict short-term stock price trends, i.e., bullish, bearish, continuation. While the charting technique is popular among traders and has long history, there is still no consistent conclusion for the predictability of the technique. The trend of stock prices often continues after intervals of several days because stock prices tend to fluctuate according to announcements of important economic indicators, economic and political news, etc. To cope with this kind of stock price characteristics, this paper focuses on a dynamic programming algorithm for retrieving similar numerical sequences. To be specific, the well-known Longest Common Subsequence (LCS) algorithm is revised to retrieve numerical sequences that partially match. The proposed algorithm also handles a relative position among a stock price, 5-day moving average, and 25-day moving average to take into account where the price occurs in price zones. Experimental results on the daily data of the Nikkei stock average show that the proposed algorithm is effective to forecast short-term trends of stock prices.

Pages: 19 to 25

Copyright: Copyright (c) IARIA, 2018

Publication date: April 22, 2018

Published in: conference

ISSN: 2519-8386

ISBN: 978-1-61208-631-6

Location: Athens, Greece

Dates: from April 22, 2018 to April 26, 2018