Title:
TECHNIQUES TO FORECAST FINANCIAL DATA USING DEEP LEARNING
Document Type and Number:
WIPO Patent Application WO/2020/186376
Kind Code:
A1
Abstract:
Disclosed are techniques to forecast financial data using deep learning. These techniques are operative to transform time series data in a financial context into a machine learning model configured to predict future financial data. The machine learning model may implement a deep learning structure to account for a sequence-sequence prediction where a movement/distribution of the time series data is non-linear. The machine learning model may incorporate features related to one or more external factors affecting the future financial data.
Inventors:
WANG DAJUN (CN)
MENG QINXUE (CN)
CHEN ZHENDI (CN)
MENG QINXUE (CN)
CHEN ZHENDI (CN)
Application Number:
PCT/CN2019/078230
Publication Date:
September 24, 2020
Filing Date:
March 15, 2019
Export Citation:
Assignee:
STATE STREET CORP (US)
WANG DAJUN (CN)
WANG DAJUN (CN)
International Classes:
G06Q10/04; G06Q40/04
Foreign References:
| CN107481048A | 2017-12-15 | |||
| CN106203731A | 2016-12-07 | |||
| CN107832897A | 2018-03-23 | |||
| US20170364998A1 | 2017-12-21 |
Other References:
PAI, PING-FENG ET AL.,: "A hybrid ARIMA and support vector machines model in stock price forecasting,", OMEGA,, 16 September 2004 (2004-09-16), pages 498 - 500, XP027843212, DOI: 20191204105515X
Attorney, Agent or Firm:
CHINA PATENT AGENT (H.K.) LTD. (CN)
Download PDF:
Previous Patent: DISPLAY DEVICE, TERMINAL AND PHOTOGRAPHING METHOD
Next Patent: WATERBORNE POLYURETHANE DISPERSION AND METHOD FOR PREPARING SAME
Next Patent: WATERBORNE POLYURETHANE DISPERSION AND METHOD FOR PREPARING SAME