Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DEEP LEARNING-BASED STOCK PRICE PREDICTION SYSTEM AND METHOD USING RECURRENT NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2019/190053
Kind Code:
A1
Abstract:
The present invention relates to a deep learning-based stock price prediction system and method using a recurrent neural network, wherein the system can improve the accuracy of prediction by machine learning various past time series data related to a stock through a deep learning model using a recurrent neural network in predicting a stock price at a next time point relative to a reference time point of a time series, then predicting the stock price with a value that represents a fluctuation of the stock price at the next time point relative to the stock price at the reference time point as a percentage or a value corresponding to the fluctuation, and dividing the prediction into high and low prices of the next time point period relative to the reference time point, and can utilize the prediction results in real transactions such as stocks or related derivatives and funds, and also enhance a rate of return on such investments.

Inventors:
YOO, Chi-Hun (#302, 52 Teheran-ro 32-gil,Gangnam-gu, Seoul, 06224, KR)
Application Number:
KR2019/001861
Publication Date:
October 03, 2019
Filing Date:
February 15, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
YOO, Chi-Hun (#302, 52 Teheran-ro 32-gil,Gangnam-gu, Seoul, 06224, KR)
International Classes:
G06Q40/06; G06N3/02; G06N20/00
Foreign References:
KR20040064884A2004-07-21
JP2017157213A2017-09-07
KR101508361B12015-04-08
JP2005004701A2005-01-06
Other References:
SMARTLY: "[Tensorflow] Predict Amazon stock price using LSTM RNN", BLOG.NAVER, 10 December 2017 (2017-12-10), Retrieved from the Internet
Attorney, Agent or Firm:
PARK, Min-Heung et al. (6F 318, Gangnam-daeroGangnam-gu, Seoul, 06253, KR)
Download PDF: