Subsequence dynamic time warping for charting: Bullish and bearish class predictions for NYSE stocks
作者：
Highlights：
• We formally state and justify a set of five common characteristics of charting.
• We propose an algorithmic scheme that captures these characteristics.
• The proposed algorithm is primarily based on subsequence Dynamic Time Warping.
• The proposed algorithm performs significantly in predicting bearish classes.
• Bearish class predictions generate on average significant maximum potential profits.
摘要
•We formally state and justify a set of five common characteristics of charting.•We propose an algorithmic scheme that captures these characteristics.•The proposed algorithm is primarily based on subsequence Dynamic Time Warping.•The proposed algorithm performs significantly in predicting bearish classes.•Bearish class predictions generate on average significant maximum potential profits.
论文关键词：Technical analysis,Pattern recognition,Dynamic time warping
论文评审过程：Received 29 September 2017, Revised 27 October 2017, Accepted 28 October 2017, Available online 31 October 2017, Version of Record 7 November 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.10.055
