Medium and long-term stock trend prediction method and system based on Bayesian classifier

Abstract

The invention relates to a medium and long-term stock trend prediction method based on a Bayesian classifier, comprising: selecting stock data, determining each starting point and interval length dj; dividing intervals, and calculating the interval slope of historical data; Carry out learning and predict the confidence judgment interval, and obtain the average stock price of multiple trading days starting from the starting point of the confidence judgment interval; calculate the confidence degree, and compare the confidence degree with the preset threshold; predict the future Interval slope, convert the future interval slope into the average stock price of multiple trading days starting from the starting point of the forecast interval; normalize the rise and fall of the average stock price of multiple trading days starting from the starting point of the forecast interval , to get the ups and downs of the stock; build a stock pool. The invention avoids accumulative errors, shows stock trend changes within the prediction interval, better captures stock market fluctuation trends, and more effectively evaluates transaction risks.

Description

technical field [0001] The present invention relates to a data processing system or method specially suitable for administration, commerce, finance, management, supervision or forecasting purposes, especially a medium and long-term stock trend forecasting method and system based on a Bayesian classifier. Background technique [0002] The stock market is an important place for the optimal allocation of capital resources, and mastering its changing laws is not only a dream for investors, but also has important practical significance for the research and management of the macro national economy. Since the factors affecting the stock price include internal factors of the enterprise, economic factors, system factors, people's psychological factors, etc., and the degree and mode of influence of various factors are different, it is very difficult to accurately predict the stock price. [0003] Time series analysis has become an indispensable part of stock market research both theor...

AI Technical Summary

Problems solved by technology

[0004] At present, the medium and long-term forecasting methods of existing stocks mainly include: using the forecast results of the previous step to iteratively and recursively obtain the subsequent medium and long-term forecast (reference example: Yang Yiwen, Lin Yupei. Fuzzy time series modeling and stock market multi-step Forecasting [J]. Computer Engineering and Application, 2014, (5): 252-256.), but there is a cumulative error in this method, and the cumulative error increases with the growth of the forecast step; using the moving window algorithm in the modeling sequence The forecasting model is recursively updated by deleting some old data and incorporating some new data (reference example: Jian Qingming, Zeng Huanglin, Ye Xiaotong. Application of support vector regression based on moving window and dynamic optimization in index forecasting[J].Computer application and Software, 2011, (12): 83-85.), the length of the moving window in this method has a great influence on the modeling accuracy, and it can only show the average stock price in the prediction interval, but cannot show the stock trend in the prediction interval changes in details

In addition, the current methods directly use the mean value as the characteristic value of stock trend prediction. For time series with large fluctuations, the mean value will weaken the fluctuation characteristics of the time period and reduce the accuracy of medium and long-term forecasting.

Images