Stock market data analysis method based on recurrent neural network optimized by dimensionality reduction technology

Abstract

The invention belongs to the technical field of financial information data processing, and discloses a stock market data analysis method based on a recurrent neural network optimized by dimensionality reduction technology. First, factor analysis is performed on the data sets, and the first and second types of prime factors are respectively extracted. class; find the parameter variable, and analyze the relationship between the parameter variable and the rise and fall of the stock over time; substitute the parameter variable into the LSTM model for prediction, and the optimized LSTM adds a forget gate to each incentive source to screen the previous information. The invention expands the LSTM neural network in the financial field, successfully applies the concept of the forget gate to stock market analysis, and improves the accuracy; it introduces a dimensionality reduction algorithm in data and processing and compares them. The invention highlights the advantages of the dimension reduction technology and the accuracy of the LSTM network, making the stock market prediction more credible than the traditional analysis method; the prediction can be applied to practice.

Description

technical field [0001] The invention belongs to the technical field of financial information data processing, and in particular relates to a stock market data analysis method based on a recurrent neural network optimized by dimensionality reduction technology. Background technique [0002] At present, the closest existing technology: principal component analysis, in the research and application of many fields, usually needs to observe the data containing multiple variables, collect a large amount of data and then analyze and find the law. Multivariate large data sets will undoubtedly provide rich information for research and application, but also increase the workload of data collection to a certain extent. More importantly, in many cases, there may be correlations between many variables, which increases the complexity of problem analysis. If each indicator is analyzed separately, the analysis is often isolated and the information in the data cannot be fully utilized, so bl...

AI Technical Summary

Problems solved by technology

[0012] (1) The existing principal component analysis method and the traditional cyclic neural network only use a small number of two or three of them to make predictions, while ignoring the rest of the indicators, resulting in inaccurate data results

[0013] (2) If the traditional RNN algorithm is optimized using the gradient descent method, there will be serious problems of "gradient disappearance" or "gradient explosion", and the accuracy of the data is low

Images