Adaptive stock prediction method of hidden Markov model based on multi-characteristic factor

Abstract

The invention discloses an adaptive stock prediction method of a HMM (hidden Markov model) based on multi-characteristic factors; the method mainly comprises stock sample data and the HMM; the stock prediction concept based on HMM comprises the following steps: marking time points of history data in a hidden state so as to classify time points; searching history points with consistent classification marks of the day before a to-be-predicted date; calculating to obtain the increase and decrease amounts of the history points and the date after the history points, and estimating the closing priceresidual errors of the to-be-predicted date and the previous day. The method uses multi-characteristic attributes, and uses stock market value capital, technology and momentum indexes as primary election characteristics; the attributes with a stronger prediction capability are selected by various methods so as to serve as characteristic vectors; compared with a method using less characteristics,the adaptive stock prediction method is better in prediction capability.

Description

technical field [0001] The invention belongs to the technical field of stock forecasting, and relates to an HMM-based stock index trend classification forecasting method. Background technique [0002] In the 1960s, Baum proposed the Hidden Markov Model, which was then widely known to researchers and enthusiasts through the use in the field of speech recognition. In 1988, Kai-fu Lee’s doctoral thesis, the speech recognition software based on HMM was evaluated. important invention. Renaissance Technology Corporation is a well-known international investment institution. Since 1989, it has maintained a super high annual rate of return and has been hailed as the most efficient hedge fund in the industry. It is through the unique mathematical model to capture market opportunities for quantitative investment. Hidden Markov models are one of the company's main tools. Therefore, it is of practical significance to try HMM for forecasting in financial markets. [0003] The stock ma...

AI Technical Summary

Problems solved by technology

[0004] At present, the research in the industry is still doing some statistical analysis models in the direction of finance, such as: pendulum theory model, small market value theory, Alpha model, attribution analysis, alpaca and turtle strategy, etc. These traditional methods have achieved ceiling, or there is no way to break through the bottleneck, you can use machine learning methods to find out more from the nature of data and the inherent natural development laws of the market without the constraints of too many financial frameworks, and there will be more Good results. At present, various algorithms have been done preliminary research in the industry, but better models still need to be optimized and improved, in order to better integrate with actual problems

Images