Stock forecasting method based on accurate high and low point segmentation matched with correlation trend

Abstract

The invention discloses a stock forecasting method based on accurate high and low point segmentation matched with the correlation trend. The main idea of the method is detecting and recording the high and low points of all the stocks in historical time series; afterwards, obtaining the trend of each to-be-forecasted stock for a most recent time period, after measuring the beginning high and low points and setting an initial model, accurately matching with the locations of the high and low points of the recorded, to be matched stocks; on this basis, calculating the trend correlations of the matched points; after having found the most correlated matched segment searched from all the stocks, the later period trend of the known, to-be-matched stocks is used to estimate the later period of to-be-forecasted stocks. The method provides very good decision support for short-term handling of stocks.

Description

technical field [0001] The invention relates to the technical field of stock data mining, in particular to a stock prediction method based on accurate high and low point segment correlation trend matching. Background technique [0002] The stock market is a market where risks and benefits coexist. The modeling and forecasting research of the stock market is of great significance to the economic development and financial construction of our country. [0003] The stock price index is mainly affected by two types of random factors, internal and external. Internal random factors are mainly affected by uncertain nonlinear factors within the system; external random factors are mainly affected by national policies, major events and other factors. It is impossible to predict the external random factors technically, but from the internal factors, the stock price index series is a nonlinear time series. The traditional forecasting method based on linear analysis technology can't acc...

AI Technical Summary

Problems solved by technology

Traditional forecasting methods based on linear analysis techniques cannot accurately describe the stock change rules, so it is difficult to obtain high-precision forecasting results

[0004] Non-linear analysis methods commonly used in stock price forecasting include: gray forecasting method, neural network, support vector machine, genetic algorithm, etc. Although the forecasting results have been improved, there are still some deficiencies, and the stock forecasting results are still far from the actual requirements. difference

Images