Stock index prediction method and device based on neural network model and time sequence

A neural network model and time series technology, which is applied in the field of stock index forecasting methods and devices based on neural network models and time series, to achieve the effect of improving accuracy and forecasting length.

Inactive Publication Date: 2019-09-20
FUJIAN JIANGXIA UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Generally speaking, stock market-related forecasting technologies are relatively mature and have a certain degree of accuracy. However, it is common to preprocess too much data or re-forecast based on data forecasting. Therefore, the forecasting accuracy and forecasting length are still urgently needed. solved problem

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
  • Stock index prediction method and device based on neural network model and time sequence
  • Stock index prediction method and device based on neural network model and time sequence
  • Stock index prediction method and device based on neural network model and time sequence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] Please refer to figure 1 , a stock index prediction method based on a neural network model and time series, including steps:

[0092] S1. Extract the time series data of the stock index to be predicted to obtain characteristic data;

[0093] S2. Preprocessing the feature data to obtain first data;

[0094] The pretreatment specifically includes one or more of the following treatments:

[0095] filling missing values ​​in the feature data by a preset filling method;

[0096] replacing the outliers in the feature data according to the correlation between the data;

[0097] Standardize the feature data;

[0098] Perform normalization processing on the feature data;

[0099] Step S2 also includes:

[0100] Judging whether the preprocessing is completed, if so, execute step S3;

[0101] S3. Perform time-series processing on the first data to obtain second data;

[0102] Step S3 is specifically:

[0103] establishing a time series model, and performing time series pr...

Embodiment 2

[0108] The difference between this embodiment and Embodiment 1 is that this embodiment will further illustrate how the above-mentioned stock index prediction method based on the neural network model and time series of the present invention is realized in combination with specific application scenarios:

[0109] 1. Time series financial data collection and preprocessing

[0110] 1. Extract the time series data of the stock index to be predicted to obtain the characteristic data;

[0111] Financial data can be roughly divided into internal data of financial institutions, data of financial market transactions, and data related to financial markets. Most of these data have relatively standardized data structures and are basically in chronological order. These financial data come from a wide range of sources, including professional financial websites such as Oriental Fortune.com, Hexun.com, NetEase Finance, Sina Finance, etc. These data can be obtained through crawler technology. I...

Embodiment 3

[0225] Please refer to figure 2 , a stock index forecasting device 1 based on a neural network model and time series, comprising a memory 2, a processor 3, and a computer program stored in the memory 2 and operable on the processor 3, which is realized when the processor 3 executes the program Each step in the first embodiment.

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 relates to a stock index prediction method and device based on a neural network model and a time sequence, and the method comprises the steps: extracting time sequence data of a to-be-predicted stock index, and obtaining feature data; preprocessing the feature data to obtain first data; performing time sequence processing on the first data to obtain second data; and training the second data through a neural network model, and predicting the price of the stock finger to be predicted, thereby improving the accuracy and length of stock finger prediction.

Description

technical field [0001] The invention relates to the field of big data financial technology, in particular to a stock index prediction method and device based on neural network models and time series. Background technique [0002] (1) Mainstream Forecast Research in Financial Markets [0003] Time, price, and trading volume are regarded as the three most basic elements in the financial market. Many basic researches are carried out around these three elements. As early as 1976, changes in trading volume and price have been described from different angles. Subsequent related technologies were expanded again, fully demonstrating the relationship between time, price, and trading volume in the financial market. Later, it evolved into the contradiction of Probablity of information-based trading (PIN), that is, the conclusion that PIN affects stock returns is significant or insignificant on a global scale. However, the western financial circles still recognize the PIN theory. More...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q40/04G06Q30/02G06N3/04G06N3/08
CPCG06Q40/04G06Q30/0206G06N3/08G06N3/045
Inventor 卢民荣陈海烽郑曈林思思
Owner FUJIAN JIANGXIA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products