Stock prediction method based on investor psychological emotion

Abstract

The invention provides a stock prediction method combining investor psychological emotion with stock market historical transaction data, and the method comprises the steps: firstly carrying out the model distillation of a BERT which is a deep bidirectional pre-training language model, obtaining distil-BERT, and meeting the business demands on the prediction precision of emotion analysis through model distillation; and reducing the scale of the sentiment analysis model so as to shorten the reasoning time of the sentiment analysis model. Finally, in the stock prediction stage, the invention designs a stock prediction method based on a multi-head attention mechanism, thereby effectively alleviating the problem of gradient explosion gradient dispersion of the LSTM recurrent neural network, andfurther improving the accuracy of stock market prediction. According to the invention, scientific and technological innovation is achieved through deep learning frontier technologies such as BERT pre-training model, model distillation, multi-head attention mechanism and the like.

Description

technical field [0001] The invention relates to the field of stock market forecasting, and more specifically, relates to a stock forecasting method combining investor psychology and stock market transaction data. Background technique [0002] Stock market forecasting has long been considered one of the most challenging studies. Changes in the stock market are a dynamic, non-linear process that combines various complex factors. The popularity of sites such as Post Bar forums, which give investors a place to post comments online, has made investor sentiment one of the key predictors of the stock market. In the research field of reviews and stock relations, more and more scholars believe that reviews usually have the subjective emotional color of the text author, that is, reviews have a certain emotional orientation. Sentiment orientation analysis, also known as sentiment analysis, is mainly used in the field of natural language processing, such as review information, microbl...

AI Technical Summary

Problems solved by technology

Aa et al find that expert sentiment signals may yield higher risk-adjusted returns

Images