期刊名称：Advances in Mathematical Finance and Applications
印刷版ISSN：2538-5569
电子版ISSN：2645-4610
出版年度：2019
卷号：4
期号：3
页码：107-125
DOI：10.22034/amfa.2019.585179.1185
语种：English
出版社：Islamic Azad University of Arak
摘要：The present research proposes an automatic system based on moving average (MA) and fuzzy logic to recognize technical analysis patterns including head and shoulder patterns, triangle patterns and broadening patterns in the Tehran Stock Exchange. The automatic system was used on 38 indicators of Tehran Stock Exchange within the period 2014-2017 in order to evaluate the effectiveness of technical patterns. Having compared the conditional distribution of daily returns under the condition of the discovered patterns and the unconditional distribution of returns at various levels of confidence driven from fuzzy logic with the mean returns of all normalized market indicators, we observed that in the desired period, after recognizing the pattern, all patterns investigated at the confidence level 0.95 with a fuzzy point 0.5 contained useful information, practically leading to abnormal returns.
