Stock trading rule prediction method based on biclustering mining and fuzzy reasoning

Abstract

The invention discloses a stock trading rule prediction method based on biclustering mining and fuzzy reasoning. The stock trading rule prediction method comprises the steps of firstly, selecting stock data in a period of time as a data set for mining biclustering, calculating a technical index value corresponding to stock original data of each day according to different technical index formulas, constructing an index matrix A=(a<ij>) <m*n>, mining the biclustering in the data set by adopting a biclustering algorithm, wherein each biclustering corresponds to a mode of trading rules in the stock data set, constructing fuzzy rules with pertinence by utilizing the mined biclustering, and finally constructing a fuzzy prediction model and predicting the trading rules according to all the obtained fuzzy rules. The prediction model provided by the stock trading rule prediction method can be used for predicting the trading rules in stock price curves, provides the best stock buying or selling reference opportunity for investors, and solves the problems in the traditional method that the rule for constructing fuzzy rules according to expert experiences is not objective and the expert experiences are difficult to obtain.

Description

technical field [0001] The invention relates to the technical field of stock financial forecasting, in particular to a stock trading rule forecasting method based on bi-cluster mining and fuzzy reasoning. Background technique [0002] The prediction of stock trading rules is a research hotspot in the field of stock finance. Many experts and investors are studying how to determine the best timing of buying and selling, but sometimes it is inevitable to get wrong results. Because of the high dimensionality and instability of stock prices, it is very difficult to predict stock trading rules. At the same time, the stock price is easily affected by various factors such as the economic environment and political form, which increases the difficulty of predicting stock trading rules to a certain extent. The original representative of stock forecasting is based on the early-developed technical analysis theory, such as average line theory, K-line chart analysis method, histogram anal...

AI Technical Summary

Problems solved by technology

[0002] The prediction of stock trading rules is a research hotspot in the field of stock finance. Many experts and investors are studying how to determine the best time to buy and sell, but sometimes it is inevitable to get wrong results

Because of the high dimensionality and instability of stock prices, it is very difficult to predict stock trading rules

At the same time, stock prices are easily affected by various factors such as the economic environment and political forms, which to a certain extent increases the difficulty of predicting stock trading rules.

The original representative of stock forecasting is based on the early-developed technical analysis theory, such as average line theory, K-line chart analysis method, histogram analysis method, etc. With the application of computer technology and data mining in the securities field, stock forecasting There are more and more methods, but most of them are only analytical means, and cannot directly predict the dynamics of the stock market.

Moreover, the biggest problem that needs to be faced by using traditional forecasting technology to predict the transformation of the stock market is that the amount of data to be processed is very large. The summary of these massive data often implies information about various trading rules. It is difficult to discover simply by people's intuition and experience

Images