Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Statistics & Decision》 2018-17
Add to Favorite Get Latest Update

Technical Analysis Method Based on Graphic Similarity

Li Daye;Li Tianyang;Business School,University of International Business and Economics;International Economics and Trading School, University of International Business and Economics;  
This paper proposes a new method based on K-nearest neighbor method, in which there is no need to pre-select the graphical object for study, but instead, the top-down data-mining of the graphic space of all patterns is used to test all possible patterns with predictive abilities. The results based on the U.S. stock daily data indicate that the actual market efficiency is close to what the efficient market assumes, and at least 60% of all graphical spaces have almost no predictive power; the top 10% of the graphs have an accuracy rate of 52.72% in the out-of-sample prediction. The results are significant at 99% confidence.
【Fund】: 中国博士后科学基金面上项目(2018M631411)
【CateGory Index】: F224;F832.51
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved