<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">msuecon</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник Московского университета. Серия 6. Экономика</journal-title><trans-title-group xml:lang="en"><trans-title>Lomonosov Economics Journal</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">0130-0105</issn><publisher><publisher-name>MSUPRESS</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.55959/MSU0130-0105-6-61-3-5</article-id><article-id custom-type="elpub" pub-id-type="custom">msuecon-1670</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ФИНАНСОВАЯ ЭКОНОМИКА</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>FINANCIAL STUDIES</subject></subj-group></article-categories><title-group><article-title>Оценка влияния новостной информации из Telegram на котировки акций нейросетями</article-title><trans-title-group xml:lang="en"><trans-title>Telegram news influence on stocks through neural networks</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0000-8430-7744</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Борисенко</surname><given-names>Г. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Borisenko</surname><given-names>G. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Москва</p></bio><bio xml:lang="en"><p>Moscow</p></bio><email xlink:type="simple">borisenko.georgiy@bk.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>МГУ им. М. В. Ломоносова</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Lomonosov Moscow State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>11</day><month>08</month><year>2026</year></pub-date><volume>61</volume><issue>3</issue><fpage>100</fpage><lpage>121</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Борисенко Г.А., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Борисенко Г.А.</copyright-holder><copyright-holder xml:lang="en">Borisenko G.A.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://msuecon.elpub.ru/jour/article/view/1670">https://msuecon.elpub.ru/jour/article/view/1670</self-uri><abstract><p>Данная работа посвящена анализу влияния новостной информации на краткосрочные колебания акций компании, к которым данная новостная информация относится. В качестве данных временных рядов используются минутные свечи котировок акций крупнейших публичных компаний на Московской бирже, новостная информация получена из популярных Telegram-каналов, посвященных новостям об экономике, бизнесу и инвестициях. Основной целью работы является оценка возможности построения нейросетевых моделей способных предсказывать краткосрочные изменения цен акций после публикации новостей. Для того чтобы сравнить качество предсказания около реальных новостей модели также строятся около синтетических новостей случайные точки во времени, которые симулируют момент выхода новости. Также для того чтобы показать стабильность результатов модели обучались и тестировались на различных подвыборках, полученных методом временной кросс-валидации. Более того, стабильность результатов продемонстрирована за счет использования различных по архитектуре нейросетей: сверточной, рекуррентной, двунаправленной рекуррентной и трансформера. В результате работы выявлено, что для всех компаний и на всех подвыборках, разделенных во времени, в среднем прогнозирование временных рядов около реальных новостей показывает качество хуже, чем прогнозирование в случайной точке, что отчасти подтверждает гипотезу эффективных рынков в слабой форме.</p></abstract><trans-abstract xml:lang="en"><p>This paper analyzes the impact of news information on short-term fluctuations of share prices of the company related to this news information. Time series data is represented by minute candles of stock quotes of the largest public companies on the Moscow Stock Exchange. News information is obtained from popular Telegram channels dealing with economic investment and business news. The main goal of the work is to assess the possibility of constructing neural network models capable of predicting short-term changes in stock prices after the publication of news. In order to compare the quality of prediction around real news, models are also built around synthetic news random points in time that simulate the moment of news release. Also, in order to show the robustness of results, the models were trained and tested on various subsamples obtained by the method of temporal cross-validation. Moreover, the stability of the results is demonstrated through the use of neural networks with different architectures: convolutional, recurrent, bidirectional recurrent and transformer. The findings reveal that for all companies and on all subsamples separated in time, on average, forecasting time series around real news shows worse quality than forecasting at a random point, which partly confirms the Efficient Markets Hypothesis in its weak form.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>нейросети</kwd><kwd>гипотеза эффективного рынка</kwd><kwd>временные ряды</kwd><kwd>сентимент</kwd></kwd-group><kwd-group xml:lang="en"><kwd>news information</kwd><kwd>neural networks</kwd><kwd>efficient market hypothesis</kwd><kwd>time series</kwd><kwd>sentiment</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Кравец, Д. А. (2021). Исследование методов прогнозирования стоимости ценных бумаг на основе машинного обучения. Информационно-телекоммуникационные технологии и математическое моделирование высокотехнологичных систем , 218–222.</mixed-citation><mixed-citation xml:lang="en">Habr (15.12.2 023). Dobrovinskiy F. LSTM and GRU. Retrieved March 01, 2025, from https://habr.com/ru/companies/mvideo/articles/780774/.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Кузнецов, Р. С., &amp; Тумарова, Т. Г. (2023). Прогнозирование котировок акций ПАО Газпром с использованием нейронных сетей LSTM. Вестник Института экономики Российской академии наук, 3 , 84–98. https://doi.org/10.52180/20736487_2023_3_84_98.</mixed-citation><mixed-citation xml:lang="en">Kravets, D. (2021). Research on methods of securities price forecasting based on machine learning. Information and telecommunication technologies and mathematical modeling of HighTech systems, 218–222.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Хабр (15.12.2023). Добровицкий Ф. LSTM и GRU. Дата обращения 01.03.2025, https://habr.com/ru/companies/mvideo/articles/780774/.</mixed-citation><mixed-citation xml:lang="en">Kuznetsov, R., &amp; Tumarova, T. (2023). PAO GAZPROM stock price prediction using lstm neural networks. Vestnik Instituta Ekonomiki Rossiyskoy akademii nauk, 3 , 84–98. https://doi.org/10.52180/2073-6487_2023_3_84_98.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Ampomah, E. K., &amp; et al. (2021). Stock market prediction with gaussian naïve bayes machine learning algorithm. Informatica, 45 (2), 243–256. https://doi.org/10.31449/inf.v45i2.3407.</mixed-citation><mixed-citation xml:lang="en">Ampomah, E. K., &amp; et al. (2021). Stock market prediction with gaussian naïve bayes machine learning algorithm. Informatica, 45 (2), 243–256. https://doi.org/10.31449/inf.v45i2.3407.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Cacciari, I., &amp; Ranfagni, A. (2024). Hands-On Fundamentals of 1D Convolutional Neural Networks A Tutorial for Beginner Users. Applied Sciences, 14 (18). https://doi.org/10.3390/app14188500.</mixed-citation><mixed-citation xml:lang="en">Cacciari, I., &amp; Ranfagni, A. (2024). Hands-On Fundamentals of 1D Convolutional Neural Networks A Tutorial for Beginner Users. Applied Sciences, 14 (18). https://doi.org/10.3390/app14188500.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Chatfield, C. (2013). The analysis of time series: theory and practice. Springer. https://doi.org/10.1007/978-1-4899-2925-9.</mixed-citation><mixed-citation xml:lang="en">Chatfield, C. (2013). The analysis of time series: theory and practice. Springer. https://doi.org/10.1007/978-1-4899-2925-9.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Fama, E. F. (1970). Efficient capital markets. Journal of finance, 25 (2), 383–417. https://doi.org/10.2307/2325486.</mixed-citation><mixed-citation xml:lang="en">Fama, E. F. (1970). Efficient capital markets. Journal of finance, 25 (2), 383–417. https://doi.org/10.2307/2325486.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">GitHub (27.06.2018). Alammar, J. The Illustrated Transformer. Дата обращения 01.03.2025, https://jalammar.github.io/illustrated-transformer/.</mixed-citation><mixed-citation xml:lang="en">GitHub (27.06.2018). Alammar, J. The Illustrated Transformer. Дата обращения 01.03.2025, https://jalammar.github.io/illustrated-transformer/.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Hvid, A. K., &amp; Kristiansen, K. L. (2021). How news affects sectoral stock prices through earnings expectations and risk premia. Danmarks Nationalbank Working Papers, 168 . https://doi.org/10.2866/688016.</mixed-citation><mixed-citation xml:lang="en">Hvid, A. K., &amp; Kristiansen, K. L. (2021). How news affects sectoral stock prices through earnings expectations and risk premia. Danmarks Nationalbank Working Papers, 168 . https://doi.org/10.2866/688016.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Ioff e, S. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint. https://doi.org/10.48550/arXiv.1502.03167.</mixed-citation><mixed-citation xml:lang="en">Ioff e, S. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint. https://doi.org/10.48550/arXiv.1502.03167.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Khaidem, L., Saha, S., &amp; Dey, S. R. (2016). Predicting the direction of stock market prices using random forest. arXiv preprint. https://doi.org/10.48550/arXiv.1605.00003.</mixed-citation><mixed-citation xml:lang="en">Khaidem, L., Saha, S., &amp; Dey, S. R. (2016). Predicting the direction of stock market prices using random forest. arXiv preprint. https://doi.org/10.48550/arXiv.1605.00003.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Leković, M. (2018). Evidence for and against the validity of efficient market hypothesi. Economic themes, 5 6 (3), 369–387. https://doi.org/10.2478/ethemes-2018-0022.</mixed-citation><mixed-citation xml:lang="en">Leković, M. (2018). Evidence for and against the validity of efficient market hypothesi. Economic themes, 5 6 (3), 369–387. https://doi.org/10.2478/ethemes-2018-0022.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Mehtab, S., &amp; Sen, J. (2020). Stock price prediction using convolutional neural networks on a multivariate timeseries. arXiv preprint. DOI: https://doi.org/10.36227/techrxiv.15088734.</mixed-citation><mixed-citation xml:lang="en">Mehtab, S., &amp; Sen, J. (2020). Stock price prediction using convolutional neural networks on a multivariate timeseries. arXiv preprint. DOI: https://doi.org/10.36227/techrxiv.15088734.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Nabipour, M. P., Nayyeri, H. J., Mosavi, A., Salwana, E., &amp; Shahab, S. (2020). Deep learning for stock market prediction. Entropy, 22 (8), 840. https://doi.org/10.3390/e22080840.</mixed-citation><mixed-citation xml:lang="en">Nabipour, M. P., Nayyeri, H. J., Mosavi, A., Salwana, E., &amp; Shahab, S. (2020). Deep learning for stock market prediction. Entropy, 22 (8), 840. https://doi.org/10.3390/e22080840.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Pang, X., Zhou, Y., Wang, P., &amp; Lin, W. (2020). An innovative neural network approach for stock market prediction. The Journal of Supercomputing, 7 6 , 2098–2118. https://doi.org/10.1007/s11227-017-2228-y.</mixed-citation><mixed-citation xml:lang="en">Pang, X., Zhou, Y., Wang, P., &amp; Lin, W. (2020). An innovative neural network approach for stock market prediction. The Journal of Supercomputing, 7 6 , 2098–2118. https://doi.org/10.1007/s11227-017-2228-y.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Suharsono, A., Aziza, A., &amp; Pramesti, W. (2017). Comparison of vector autoregressive (VAR) and vector error correction models (VECM) for index of ASEAN stock price. AIP Conference Proceedings, 1913(1). https://doi.org/10.1063/1.5016666.</mixed-citation><mixed-citation xml:lang="en">Suharsono, A., Aziza, A., &amp; Pramesti, W. (2017). Comparison of vector autoregressive (VAR) and vector error correction models (VECM) for index of ASEAN stock price. AIP Conference Proceedings, 1913(1). https://doi.org/10.1063/1.5016666.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Volodin, S. N., Kuranov, G. M., &amp; Yakubov, A. P. (2017). Impact of Political News: Evidence from Russia. Scientific Annals of Economics and Business, 64 (3), 271–287. https://doi.org/10.1515/saeb-2017-0018.</mixed-citation><mixed-citation xml:lang="en">Volodin, S. N., Kuranov, G. M., &amp; Yakubov, A. P. (2017). Impact of Political News: Evidence from Russia. Scientific Annals of Economics and Business, 64 (3), 271–287. https://doi.org/10.1515/saeb-2017-0018.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Wang, C., Chen, Y., Zhang, S., &amp; Zhang, Q. (2022). Stock market index prediction using deep Transformer model. Expert Systems with Applications, 208 , 118–128. https://doi.org/10.1016/j.eswa.2022.118128.</mixed-citation><mixed-citation xml:lang="en">Wang, C., Chen, Y., Zhang, S., &amp; Zhang, Q. (2022). Stock market index prediction using deep Transformer model. Expert Systems with Applications, 208 , 118–128. https://doi.org/10.1016/j.eswa.2022.118128.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Xie, L., Chen, Z., &amp; Yu, S. (2024). Deep Convolutional Transformer Network for Stock Movement Prediction. Electronics, 13 (21), 4225. https://doi.org/10.3390/electronics13214225.</mixed-citation><mixed-citation xml:lang="en">Xie, L., Chen, Z., &amp; Yu, S. (2024). Deep Convolutional Transformer Network for Stock Movement Prediction. Electronics, 13 (21), 4225. https://doi.org/10.3390/electronics13214225.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang, J., Ye, L., &amp; Lai, Y. (2023). Stock price prediction using CNN-BiLSTM-Attention model. Mathematics, 11 (9), 1985. https://doi.org/10.3390/math11091985.</mixed-citation><mixed-citation xml:lang="en">Zhang, J., Ye, L., &amp; Lai, Y. (2023). Stock price prediction using CNN-BiLSTM-Attention model. Mathematics, 11 (9), 1985. https://doi.org/10.3390/math11091985.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
