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

Stock recommending method based on inter-stock co-occurrence statistics

A recommendation method and stock technology, applied in computing, instrumentation, finance, etc., can solve problems such as unsatisfactory prediction accuracy and difficulty in establishing mathematical models

Inactive Publication Date: 2017-01-25
洪志令
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Then the stock price is a dynamic, non-linear complex system, which has the characteristics of suddenness, randomness and regularity. The forecast of the stock is affected by many factors, and it is difficult to establish a definite relationship between the stock and these factors. mathematical model
Currently commonly used stock prediction models include: regression analysis, time series method, Markov prediction, support vector machine, neural network, etc., but overall the prediction accuracy is not ideal

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 recommending method based on inter-stock co-occurrence statistics
  • Stock recommending method based on inter-stock co-occurrence statistics
  • Stock recommending method based on inter-stock co-occurrence statistics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in detail below in conjunction with the accompanying drawings and examples.

[0025] The method of the invention judges the next day's ups and downs of the stock by counting the probability of a big rise or a big fall between different stocks in the day before and after the day, and recommends the stock according to the size of the corresponding probability.

[0026] The method of the invention performs co-occurrence statistical mining on the daily data of all stocks. Due to the stock’s rise and fall and the total number of stocks are large, if the co-occurrence statistics are directly carried out, the amount of data is very large, and the number of co-occurrences is too sparse. There are 2 categories, namely big rise (>=2%) and big fall (<=-2%). Specifically defined values ​​are adjustable as parameters. The "big rise" or "big drop" mentioned below all indicate the corresponding rise and fall.

[0027] Suppose the stock list i...

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 discloses a stock recommendation method based on co-occurrence statistics among stocks. The main idea of ​​the method is to first divide the rise and fall of stocks into two situations: big rise and big fall, and then obtain the daily data of all stocks for co-occurrence statistics, and generate big rise and big fall according to the support and confidence Rules; then adapt the rules based on the rise and fall of the stocks in each trading day, and obtain the stocks that make the rules true and the corresponding confidence; finally, recommend the stocks after sorting according to the confidence. There are two types of recommendations, one is a big rise recommendation, and the other is a big drop warning. The method can provide decision support for short-term operation of stocks.

Description

technical field [0001] The invention relates to the technical field of stock data mining, in particular to a stock recommendation method based on co-occurrence statistics among stocks. Background technique [0002] The stock market has high-yield characteristics and high-risk at the same time. If investors can predict the future stock price more accurately, they can properly adjust strategies to reduce risks and obtain greater economic benefits. [0003] Then the stock price is a dynamic, non-linear complex system, which has the characteristics of suddenness, randomness and regularity. The forecast of the stock is affected by many factors, and it is difficult to establish a definite relationship between the stock and these factors. mathematical model. Currently commonly used stock forecasting models include: regression analysis, time series, Markov forecasting, support vector machines, neural networks, etc., but overall the forecasting accuracy is not ideal. [0004] Since...

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): G06Q40/04
CPCG06Q40/04
Inventor 吴梅红洪志令
Owner 洪志令