Stock prediction method fusing generative adversarial network and two-dimensional attention mechanism

Abstract

The invention discloses a stock prediction method fusing a generative adversarial network and a two-dimensional attention mechanism. The method comprises the following steps: acquiring historical sequence data of a driving factor as stock sequence input; preprocessing the historical sequence data; divdiing the preprocessed historical sequence data into a training set and a test set, performing standardization, and generating two-dimensional data sequence input; weighting spatial attention of the two-dimensional data sequence input; weighting time attention pf the two-dimensional data sequence input after the space attention weighting; constructing a stock prediction preliminary model based on a two-dimensional time-space attention mechanism as a generator; modifying an output part structure of the generator to obtain a new generator; establishing a stock prediction model based on a newborn generator and a generative adversarial network discriminator; and constructing an optimization target of the stock prediction model to obtain an optimal stock prediction model. According to the invention, a more accurate and ideal stock price prediction result can be generated.

Description

technical field [0001] The invention belongs to the field of stock forecasting and time series trend forecasting, and in particular relates to a stock forecasting method fused with a generative confrontation network and a two-dimensional attention mechanism. Background technique [0002] As one of the pillars of the financial industry, the stock market plays the role of capital accumulation and capital circulation. Using existing information to predict stock sequences is not only conducive to investors making reasonable investment decisions, obtaining stable and reasonable returns, and avoiding excessive investment risks, but also conducive to improving the effectiveness of the capital market and promoting the rational and effective allocation of capital. [0003] The stock market is a complex social system affected by many factors such as economy, politics, and industrial structure. Therefore, stock prices change rapidly and the influencing factors are intricate. Typical d...

AI Technical Summary

Problems solved by technology

On the one hand, the history of the Chinese stock market is still not long enough, and the daily transaction data is still relatively small, which is prone to model overfitting, so scholars often use methods such as regularization or dropout to improve the performance of the model; on the other hand, the current mainstream methods focus on Based on the construction of the generative model, we tried to improve the quality of the generated data by introducing a data-driven deep learning method and improving the quality of the data through data preprocessing, but did not try to introduce a discriminative model in series at the back end to further improve the performance of the generative model.

Images