Media information tensor supervised learning-based stock price fluctuation prediction system and method

Abstract

The invention discloses a media information tensor supervised learning-based stock price fluctuation prediction system and method. Tensors are built according to media information, and a supervised learning method is used for predicting stock price fluctuations. The stock price fluctuation prediction system and method are advantageous in that (1) the system and method are based on three dimension attribute information including market transaction information, stock investor emotion information and media news information; a quantitative information source and a qualitative information source are included, official new information and social media information are included, and therefore relations between Internet medias and stock markets can be analyzed comprehensively; (2) the tensors are used for representing media information space, and relations between information of different dimensions can be recorded; (3) expansion from vector-based computer learning algorithms to tensor-based computer learning algorithms is realized via the tensor supervised learning algorithm.

Description

technical field [0001] The invention relates to a stock price fluctuation prediction system and method, in particular to a stock price fluctuation prediction system and method based on media information tensor supervised learning. Background technique [0002] With the development of information technology, Internet media has gradually become the mainstream media form. Especially with the rise of social media such as blogs, Weibo, social news, Wikipedia and online forums, their media influence is increasing day by day. Massive information and fissile communication make Internet media have a decisive impact on the stock market. [0003] In the prior art, when predicting stock price fluctuations, most of the quantitative information in Internet media, such as stock trading prices, is considered, while qualitative information, such as company news, is ignored, resulting in inaccurate stock price fluctuation predictions. [0004] When combining different latitude information t...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, to provide a stock price fluctuation prediction system and method based on media information tensor supervised learning, to solve the problem of low accuracy in the existing stock price fluctuation prediction

Images