Home // International Journal On Advances in Systems and Measurements, volume 13, numbers 3 and 4, 2020 // View article

Statistical Approach to Evaluating Profitability of Stock Markets

Authors:
Yoshihisa Udagawa

Keywords: stock price prediction; technical analysis; candlestick patterns; market exit criteria; trailing stop; profit simulation; global market comparison; regression analysis.

Abstract:
Candlestick charting is one of the most popular techniques used to predict short-term stock price trends. Despite popularity, there is still no consistent conclusion for the predictability of the technique mainly due to qualitative description of candlestick patterns. This paper proposes a six parameters model that allows us to define both candlestick patterns and price zones where the patterns occur. It is important to grasp buy and sell opportunities for a successful stock trade. Uptrend reversal candlestick patterns are used to find a buy opportunity to enter a trade in a long position. Three exit criteria are proposed to find a sell opportunity to exit a trade for fixing profits or losses. Simulations to estimate profits of markets are performed using historical daily stock data of the US and Asian stock markets with approximately the same parameter values for the six parameters model and the exit criteria in terms of the standard deviation in statistics. Profitability of the proposed stock trade method is statistically examined by linear regression analysis showing that timing to sell stock is significantly related to profits for the three exit criteria. The results of simulations indicate that the US markets are more profitable than Asian markets under the proposed model.

Pages: 300 to 311

Copyright: Copyright (c) to authors, 2020. Used with permission.

Publication date: December 30, 2020

Published in: journal

ISSN: 1942-261x