ASSESSMENT OF THE EFFECTIVENESS OF APPLYING GENERATIVE ADVERSARY NEURAL NETWORK TAKEN INTO ACCOUNT OF HISTORICAL DATA AND ASSESSMENT OF TEXT TONE FOR ANALYSIS OF STOCKS IN THE STOCK MARKET

Tereshenko Andrey Alekseevich

This publication is part of a study in the field of systems analysis of the stock market and focuses on assessing the effectiveness of the use of generative adversarial neural networks (GAN) taking into account historical data and sentiment analysis of the text. The author considers the possibility of using this technology to analyze the dynamics of shares on the stock market. The results of the study are of particular interest because the author suggests that predicting stock prices is impossible. This aspect becomes especially relevant in the context of using neural networks to test this statement.

Keywords:Neural networks, dataset, system analysis, discriminator, sentiment assessment.