Title :
Stock prediction by searching similar candlestick charts
Author_Institution :
Dept. of Inf. Manage., Nat. Central Univ., Jhongli, Taiwan
Abstract :
This research applies the content-based image retrieval (CBIR) technique for stock prediction. In particular, low-level image features, including wavelet texture and Canny edge are extracted from candlestick charts. Then, similar historical candlestick charts represented by the low-level features to the query chart are retrieved, in which the `future´ stock movements of the retrieved charts are used for predicting the stock price of the query chart.
Keywords :
content-based retrieval; feature extraction; financial data processing; image retrieval; image texture; stock markets; wavelet transforms; CBIR technique; Canny edge; candlestick chart; content-based image retrieval; low-level image feature; query chart; stock prediction; stock price; wavelet texture; Feature extraction; Finance; Image edge detection; Market research; Signal to noise ratio; Vectors; Visualization;
Conference_Titel :
Data Engineering Workshops (ICDEW), 2013 IEEE 29th International Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-5303-8
Electronic_ISBN :
978-1-4673-5302-1
DOI :
10.1109/ICDEW.2013.6547474
