Stock transaction behavior prediction method based on bi-clustering excavation and Naive Bayes and AdaBoost

A forecasting method and stock trading technology, applied in forecasting, instrumentation, finance, etc., can solve problems such as difficulty in stock forecasting, instability, etc., and achieve the effects of pertinence, efficiency improvement, and reliability assurance

Inactive Publication Date: 2017-10-24
SOUTH CHINA UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The prediction of stock trading behavior is a research hotspot in the financial field. Many scholars and experts are studying how to choose the best buying time and ho

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 transaction behavior prediction method based on bi-clustering excavation and Naive Bayes and AdaBoost
  • Stock transaction behavior prediction method based on bi-clustering excavation and Naive Bayes and AdaBoost
  • Stock transaction behavior prediction method based on bi-clustering excavation and Naive Bayes and AdaBoost

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 It is a flow chart of the stock trading behavior prediction method based on bicluster mining, naive Bayesian and AdaBoost disclosed by the present invention, as figure 1 As shown, the stock trading prediction method disclosed in this embodiment specifically includes the following steps:

[0046] S1. Calculate the future rate of return FRR on the i-th trading day in the historical stock data i .

[0047] Select the stock data for a period of time as the training set for stock forecasting, and calculate the stock raw data (including opening price, highest price, lowest price, closing price and trading volume) corresponding to each trading day according to different technical index formulas. At the same time, calculate the future rate of return FRR corresponding to each trading day. The specific steps are as follows:

[0048] S11, select the stock historical data of m days as the training sample of prediction model, as the data set of biclustering mining;

[...

Embodiment 2

[0077] The present embodiment selects specific stock—Apple Corporation (AAPL), and adopts the stock trading behavior prediction method based on bicluster mining and naive Bayesian and AdaBoost to predict the price change trend of the stock, specifically including the following steps:

[0078]1) Select the stock data (opening price, highest price, lowest price, closing price and trading volume) of Apple Inc. (AAPL) for m=365 days as the training set of the stock prediction model, and at the same time as the data set for mining stock information. Select 33 stock technical index values ​​as the parameter indicators of each trading day, and calculate the future rate of return FRR of each trading day at the same time. The specific calculation formula is as follows:

[0079] For the i-th trading day and the following t trading days, the average closing price corresponding to the i-th trading day is: Among them, ACP i Indicates the average closing price of the i-th trading day, CP...

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 trading behavior prediction method based on biclustering mining, naive Bayesian and AdaBoost, which selects stock data within a certain period of time as the training set of the forecasting model, and first utilizes biclustering algorithm to mine stock data. According to different stock technical indicators, the stock price change trend can be divided into three situations: rising, flat and falling, which correspond to the buying point, holding point and selling point in stock trading. Then use the mined transaction patterns to construct a classifier based on Naive Bayesian, and finally use the AdaBoost algorithm to combine multiple weak classifiers to form a strong classifier with strong generalization ability and high classification accuracy. The proposed method can predict the changing trend of stock prices and provide valuable reference for investors' trading behavior.

Description

technical field [0001] The invention relates to the technical field of stock financial forecasting, in particular to a stock trading behavior forecasting method based on bicluster mining, naive Bayesian and AdaBoost. Background technique [0002] The prediction of stock trading behavior is a research hotspot in the financial field. Many scholars and experts are studying how to choose the best buying time and how to judge the appropriate selling time. However, due to the instability and high dimensionality of stock prices For a long time, stock forecasting has always been difficult. [0003] The stock price is a set of time-continuous series. When the stock price is in an upward trend, its corresponding index parameters often show similar characteristics; when the stock price is in a downward trend or flat trend. Therefore, when predicting the price change trend of a stock, it can be solved by the classification algorithm in machine learning. Common classification models ma...

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): G06Q10/04G06Q40/04
CPCG06Q10/04G06Q40/04
Inventor 黄庆华孔舟帆杨杰
Owner SOUTH CHINA UNIV OF TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap