MATHEMATICAL METHODS FOR FORECASTING THE COST OF MARKET ASSETS: INFORMATION BACKGROUND AS A MARKET MEDIATOR

UDC 338.1
DOI: 10.36871/2618-9976.2023.12.003

Authors

Evgeny A. Konnikov,
David P. Marshalov,
Sergei V. Bekishev,
Yuriy Yu. Kochinev,
Laszlo Ungvari,
Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Russia

Abstract

This article discusses the relationship between the tone of news articles and its impact on the share price of PJSC Gazprom. About four thousand articles related to the company were collected for the study. The resulting data was preprocessed and normalized to obtain the sentiment coefficient. Next, a ridge regression model was used to explain the percentage of stock price fluctuations due to news sentiment. To reflect the impact of news on stock prices, the analysis included a delay of one day, assuming that the news effect would affect the stock price on the next trading day. The results of the study showed a determination coefficient of 16%, which indicates a moderate relationship between the sentiment of news texts and the price of PJSC Gazprom shares.

Keywords

Financial market, Information environment, Securities market, Ridge regression, Correlation, Gazprom