Unlock instant, AI-driven research and patent intelligence for your innovation.

Financial information prediction method and device based on deep learning

A technology of deep learning and prediction methods, applied in the computer field, can solve problems such as poor accuracy and stability, and achieve the effect of improving accuracy and stability

Pending Publication Date: 2019-09-27
FUJIAN JIANGXIA UNIV
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Generally speaking, the existing forecasting methods still have poor forecasting accuracy and stability, and there is no forecasting method for currency in financial information forecasting

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Financial information prediction method and device based on deep learning
  • Financial information prediction method and device based on deep learning
  • Financial information prediction method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] Please refer to figure 1 , a financial information prediction method based on deep learning, including steps:

[0079] S1. Collect the financial time series data to be predicted and obtain the input matrix;

[0080] Step S1 is specifically:

[0081] Collect the financial time series data to be predicted, and perform preprocessing to obtain the input matrix;

[0082] The pretreatment specifically includes one or more of the following treatments:

[0083] Fill the missing values ​​in the financial time series data to be predicted by the preset filling method;

[0084] Perform normalization processing on the financial time series data to be predicted;

[0085] Sorting the financial time series data to be predicted in chronological order;

[0086] S2. According to the financial time series data, a weight matrix is ​​obtained through principal component analysis calculation;

[0087] Step S2 is specifically:

[0088] S21. Standardize the financial time series data, an...

Embodiment 2

[0095] This embodiment will further illustrate how the above-mentioned deep learning-based financial information forecasting method of the present invention is realized in combination with specific application scenarios. This forecasting method is mainly developed for the interest rate and reserves of the macro monetary policy in financial information:

[0096] (1) Construct a two-way financial risk system and data set

[0097] (1) Build a two-way financial risk system

[0098] Due to the many elements of the financial market, the main risk indicators affecting the financial market in the world mainly include four aspects: macro index, currency, bond market, and stock market, and the impact of the stock market on the financial market and national policies is increasing. The present invention refers to the research results of many scholars at home and abroad on the financial market, financial risk and macro-control and other related factors, and consults the opinions of relevan...

Embodiment 3

[0218] Please refer to figure 2 , a financial information prediction device 1 based on deep learning, comprising a memory 2, a processor 3, and a computer program stored in the memory 2 and operable on the processor 3, the processor 3 implements the program when executing the program Steps in Example 1.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a financial information prediction method and device based on deep learning, and the method comprises the steps: collecting to-be-predicted financial time sequence data, and obtaining an input matrix; obtaining a weight matrix through principal component analysis and calculation according to the financial time sequence data; and according to the input matrix and the weight matrix, carrying out training through a neural network model to obtain a prediction result. The accuracy and stability of financial information prediction are improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for predicting financial information based on deep learning. Background technique [0002] In the existing research on monetary policy and financial markets, the focus is on the effectiveness of monetary policy, the transmission mechanism, and regulatory expectations. Some scholars have proposed to decompose the monetary policy tool interest rate and money supply based on the ARIMA model in the application of models and methods, and Based on the new Keynesian cycle theory to analyze the expectations of monetary policy regulation and the level of capital supply and demand in the economic cycle, some scholars have also established new methods and models, such as the proposed inflation forecasting target method, GMM model, DSGE model, etc., which are all important for monetary policy regulation. Serve as a good reference. In recent years, with the rapi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/04G06Q40/02G06N3/04
CPCG06Q10/04G06Q40/02G06N3/045
Inventor 卢民荣
Owner FUJIAN JIANGXIA UNIV