<?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">finance</journal-id><journal-title-group><journal-title xml:lang="ru">Финансы: теория и практика/Finance: Theory and Practice</journal-title><trans-title-group xml:lang="en"><trans-title>Finance: Theory and Practice</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2587-5671</issn><issn pub-type="epub">2587-7089</issn><publisher><publisher-name>Financial University under The Government of Russian Federation</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.26794/2587-5671-2018-22-5-141-153</article-id><article-id custom-type="elpub" pub-id-type="custom">finance-757</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>ПУБЛИКАЦИИ МОЛОДЫХ УЧЕНЫХ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>PUBLICATIONS OF YOUNG SCIENTISTS</subject></subj-group></article-categories><title-group><article-title>Моделирование изменения цены биржевого инструмента на базе микроструктурных рыночных данных</article-title><trans-title-group xml:lang="en"><trans-title>Modeling Stock Price Changes Based on Microstructural Market Data</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-0321-785X</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Билев</surname><given-names>Н.  А. </given-names></name><name name-style="western" xml:lang="en"><surname>Bilev</surname><given-names>N. A. </given-names></name></name-alternatives><bio xml:lang="ru"/><bio xml:lang="en"/><email xlink:type="simple">bilevn@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Московский государственный университет им. М. В. Ломоносова,&#13;
Москва</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Lomonosov Moscow State university, Mosocow</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2018</year></pub-date><pub-date pub-type="epub"><day>23</day><month>11</month><year>2018</year></pub-date><volume>22</volume><issue>5</issue><fpage>141</fpage><lpage>153</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Билев Н.А., 2018</copyright-statement><copyright-year>2018</copyright-year><copyright-holder xml:lang="ru">Билев Н.А.</copyright-holder><copyright-holder xml:lang="en">Bilev N.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://financetp.fa.ru/jour/article/view/757">https://financetp.fa.ru/jour/article/view/757</self-uri><abstract><p>На современных биржевых площадках, где большинство операций совершается посредством электронных транзакций, появляется возможность анализировать событийные микроструктурные рыночные данные. Они описывают физическое формирование цены на биржевые инструменты и обладают высокой информативностью, позволяя торговой системе находить сложные закономерности в поведении цены. Выявление таких закономерностей вручную является очень трудоемким процессом. Однако современные модели машинного обучения способны решать подобные задачи автоматически, подстраиваясь под постоянно меняющееся поведение рынка. В данной работе разрабатывается торговая система на базе модели машинного обучения и микроструктурных рыночных данных. Для исследования собрана информация с московской биржи ММВБ о событийных изменениях биржевой книги заявок и ленте всех сделок по ликвидному биржевому инструменту. Для моделирования используется модель логистической регрессии и ряд моделей искусственных нейронных сетей. Результаты исследования демонстрируют, что модель логистической регрессии не уступает в качестве прогнозирования более сложным моделям и при этом имеет высокую скорость формирования прогноза, что очень важно при принятии торгового решения на современных торговых площадках. Разработанная торговая система имеет среднюю частоту заключения сделок, что позволяет избежать дорогой инфраструктуры по сравнению с высокочастотной биржевой торговлей, но при этом дает возможность использовать весь потенциал высококачественных микроструктурных рыночных данных. Статья описывает все этапы построения торговой системы, включая выбор признаков для моделирования, сравнительный анализ моделей прогнозирования изменения цены, а также создание торгового алгоритма с тестированием на исторических данных. Он может применяться различными инвестиционными институтами для эффективного управления капиталом в биржевых торгах. Разработка более сложных и детальных торговых алгоритмов на базе модели машинного обучения позволит увеличить конечную эффективность всей торговой системы.</p></abstract><trans-abstract xml:lang="en"><p>In modern electronic stock exchanges there is an opportunity to analyze event driven market microstructure data. This data is highly informative and describes physical price formation which makes it possible to find complex patterns in price dynamics. It is very time consuming and hard to find this kind of patterns by handcrafted rules. However, modern machine learning models are able to solve such issues automatically by learning price behavior which is always changing. The present study presents profitable trading system based on a machine learning model and market microstructure data. Data for the research was collected from Moscow stock exchange MICEX and represents a limit order book change log and all market trades of a liquid security for a certain period. Logistic regression model was used and compared to neural network models with different configuration. According to the study results logistic regression model has almost the same prediction quality as neural network models have but also has a high speed of response which is very important for stock market trading. The developed trading system has medium frequency of deals submission that lets it to avoid expensive infrastructure which is usually needed in high-frequency trading systems. At the same time, the system uses the potential of high quality market microstructure data to the full extent. This paper describes the entire process of trading system development including feature engineering, models behavior comparison and creation of trading strategy with testing on historical data.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>биржевая торговля</kwd><kwd>алгоритмическая торговля</kwd><kwd>микроструктурные рыночные данные</kwd><kwd>биржевая книга заявок</kwd><kwd>машинное обучение</kwd><kwd>временные ряды</kwd><kwd>инвестиции</kwd><kwd>управление капиталом</kwd></kwd-group><kwd-group xml:lang="en"><kwd>stock market trading</kwd><kwd>algorithmic trading</kwd><kwd>market microstructure</kwd><kwd>limit order book</kwd><kwd>machine learning</kwd><kwd>time series</kwd><kwd>investment</kwd><kwd>capital management</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">Cartea A., Penalva J. Where is the value in high frequency trading? Quarterly Journal of Finance. 2012;2(3). DOI: 10.1142/S 2010139212500140</mixed-citation><mixed-citation xml:lang="en">Cartea A., Penalva J. Where is the value in high frequency trading? Quarterly Journal of Finance. 2012;2(3). DOI: 10.1142/S 2010139212500140</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Brunzell T. High­frequency trading — to regulate or not to regulate — that is the question? Does scientifc data offer an answer? Journal of Business and Financial Affairs. 2013;2(1):1–4. DOI: 10.4172/2167–0234.1000e121</mixed-citation><mixed-citation xml:lang="en">Brunzell T. High­frequency trading — to regulate or not to regulate — that is the question? Does scientifc data offer an answer? Journal of Business and Financial Affairs. 2013;2(1):1–4. DOI: 10.4172/2167–0234.1000e121</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">O’Hara M. High frequency market microstructure. Journal of Financial Economics. 2015;116(2):257–270. DOI: 10.1016/j.jfneco.2015.01.003</mixed-citation><mixed-citation xml:lang="en">O’Hara M. High frequency market microstructure. Journal of Financial Economics. 2015;116(2):257–270. DOI: 10.1016/j.jfneco.2015.01.003</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Hoffmann P. A dynamic limit order market with fast and slow traders. Journal of Financial Economics. 2014;113(1):156–169. DOI: 10.1016/j.jfneco.2014.04.002</mixed-citation><mixed-citation xml:lang="en">Hoffmann P. A dynamic limit order market with fast and slow traders. Journal of Financial Economics. 2014;113(1):156–169. DOI: 10.1016/j.jfneco.2014.04.002</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Kercheval A.N., Zhang Y. Modelling high­frequency limit order book dynamics with support vector machines. Quantitative Finance. 2015;15(8):1315–1329. DOI: 10.1080/14697688.2015.1032546</mixed-citation><mixed-citation xml:lang="en">Kercheval A.N., Zhang Y. Modelling high­frequency limit order book dynamics with support vector machines. Quantitative Finance. 2015;15(8):1315–1329. DOI: 10.1080/14697688.2015.1032546</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Anderson E., Merolla P., Pribula A. Adaptive strategies for high frequency trading. Journal of Stellar MS&amp;E. 2008. URL: https://web.stanford.edu/class/msande444/2008/OrderBook.pdf (accessed 28.08.2018).</mixed-citation><mixed-citation xml:lang="en">Anderson E., Merolla P., Pribula A. Adaptive strategies for high frequency trading. Journal of Stellar MS&amp;E. 2008. URL: https://web.stanford.edu/class/msande444/2008/OrderBook.pdf (accessed 28.08.2018).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Kearns M., Nevmyvaka Yu. Machine learning for market microstructure and high frequency trading. In: High frequency trading: New realities for traders, markets and regulators. London: Risk Books; 2013:91–124. URL: https://www.cis.upenn.edu/~mkearns/papers/KearnsNevmyvakaHFTRiskBooks.pdf (accessed 28.08.2018).</mixed-citation><mixed-citation xml:lang="en">Kearns M., Nevmyvaka Yu. Machine learning for market microstructure and high frequency trading. In: High frequency trading: New realities for traders, markets and regulators. London: Risk Books; 2013:91–124. URL: https://www.cis.upenn.edu/~mkearns/papers/KearnsNevmyvakaHFTRiskBooks.pdf (accessed 28.08.2018).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Huang H., Kercheval A. N. A generalized birth­death stochastic model for high­frequency order book dynamics. Quantitative Finance. 2012;12(4):547–557. DOI: 10.1080/14697688.2012.664926</mixed-citation><mixed-citation xml:lang="en">Huang H., Kercheval A. N. A generalized birth­death stochastic model for high­frequency order book dynamics. Quantitative Finance. 2012;12(4):547–557. DOI: 10.1080/14697688.2012.664926</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Goldstein M.A., Kumar P.K., Graves F.C. Computerized and high­frequency trading. The Financial Review. 2014;49(2):177–202. DOI: 10.1111/fre.12031</mixed-citation><mixed-citation xml:lang="en">Goldstein M.A., Kumar P.K., Graves F.C. Computerized and high­frequency trading. The Financial Review. 2014;49(2):177–202. DOI: 10.1111/fre.12031</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Angel J., L. Harris L., Spatt C.S. Equity trading in the 21st century. Quarterly Journal of Finance. 2011;1(1):1–53. DOI: 10.1142/S 2010139211000067</mixed-citation><mixed-citation xml:lang="en">Angel J., L. Harris L., Spatt C.S. Equity trading in the 21st century. Quarterly Journal of Finance. 2011;1(1):1–53. DOI: 10.1142/S 2010139211000067</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Bishop C.M. Pattern recognition and machine learning. New York: Springer­Verlag; 2006. 738 p.</mixed-citation><mixed-citation xml:lang="en">Bishop C.M. Pattern recognition and machine learning. New York: Springer­Verlag; 2006. 738 p.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Patel J., Shah S., Thakkar P., Kotecha K. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert Systems with Applications. 2015;42(1):259–268. DOI: 10.1016/j.eswa.2014.07.040</mixed-citation><mixed-citation xml:lang="en">Patel J., Shah S., Thakkar P., Kotecha K. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert Systems with Applications. 2015;42(1):259–268. DOI: 10.1016/j.eswa.2014.07.040</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Tsantekidis A., Passalis N., Tefas A., Kanniainen J., Gabbouj M., Iosifdis A. Forecasting stock prices from the limit order book using convolutional neural networks. In: IEEE 19th Conf. on business informatics (CBI) (Thessaloniki, Greece, 24–27 July 2017). New York: IEEE; 2017. DOI: 10.1109/CBI.2017.23</mixed-citation><mixed-citation xml:lang="en">Tsantekidis A., Passalis N., Tefas A., Kanniainen J., Gabbouj M., Iosifdis A. Forecasting stock prices from the limit order book using convolutional neural networks. In: IEEE 19th Conf. on business informatics (CBI) (Thessaloniki, Greece, 24–27 July 2017). New York: IEEE; 2017. DOI: 10.1109/CBI.2017.23</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Achelis S.B. Technical analysis from A to Z: Covers every trading tool… from the Absolute Breadth Index to the Zig Zag. New York: McGraw­Hill Co.; 2000. 380 p.</mixed-citation><mixed-citation xml:lang="en">Achelis S.B. Technical analysis from A to Z: Covers every trading tool… from the Absolute Breadth Index to the Zig Zag. New York: McGraw­Hill Co.; 2000. 380 p.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Cox D.R. The regression analysis of binary sequences (with discussion). Journal of the Royal Statistical Society: Series B. 1958;20(2):215–242. URL: https://www.nuffeld.ox.ac.uk/users/cox/cox48.pdf (accessed 28.08.2018).</mixed-citation><mixed-citation xml:lang="en">Cox D.R. The regression analysis of binary sequences (with discussion). Journal of the Royal Statistical Society: Series B. 1958;20(2):215–242. URL: https://www.nuffeld.ox.ac.uk/users/cox/cox48.pdf (accessed 28.08.2018).</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Clevert D.­A., Unterthiner T., Hochreiter S. Fast and accurate deep network learning by exponential linear units (ELUs). In: 4th Int. conf. on learning representations (ICLR 2016) (San Juan, Puerto Rico, 2–4 May, 2016). URL: https://arxiv.org/pdf/1511.07289.pdf</mixed-citation><mixed-citation xml:lang="en">Clevert D.­A., Unterthiner T., Hochreiter S. Fast and accurate deep network learning by exponential linear units (ELUs). In: 4th Int. conf. on learning representations (ICLR 2016) (San Juan, Puerto Rico, 2–4 May, 2016). URL: https://arxiv.org/pdf/1511.07289.pdf</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research. 2014;15(1):1929–1958. URL: http://jmlr.org/papers/volume15/srivastava14a.old/srivastava14a.pdf (accessed 28.08.2018).</mixed-citation><mixed-citation xml:lang="en">Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research. 2014;15(1):1929–1958. URL: http://jmlr.org/papers/volume15/srivastava14a.old/srivastava14a.pdf (accessed 28.08.2018).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Kingma D.P., Ba J. Adam: A method for stochastic optimization. In: 3rd Int. conf. on learning representations (ICLR 2015) (San Diego, 7–9 May, 2015). URL: https://arxiv.org/pdf/1412.6980.pdf (accessed 28.08.2018).</mixed-citation><mixed-citation xml:lang="en">Kingma D.P., Ba J. Adam: A method for stochastic optimization. In: 3rd Int. conf. on learning representations (ICLR 2015) (San Diego, 7–9 May, 2015). URL: https://arxiv.org/pdf/1412.6980.pdf (accessed 28.08.2018).</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Rosasco L., De Vito E. D., Caponnetto A., Piana M., Verri A. Are loss functions all the same? Neural Computation. 2004;16(5):1063–1076. DOI: 10.1162/089976604773135104</mixed-citation><mixed-citation xml:lang="en">Rosasco L., De Vito E. D., Caponnetto A., Piana M., Verri A. Are loss functions all the same? Neural Computation. 2004;16(5):1063–1076. DOI: 10.1162/089976604773135104</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Li X., Deng X., Zhu S., Wang F., Xie H. An intelligent market making strategy in algorithmic trading. Frontiers of Computer Science. 2014;8(4):596–608. DOI: 10.1007/s11704–014–3312–6</mixed-citation><mixed-citation xml:lang="en">Li X., Deng X., Zhu S., Wang F., Xie H. An intelligent market making strategy in algorithmic trading. Frontiers of Computer Science. 2014;8(4):596–608. DOI: 10.1007/s11704–014–3312–6</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Powers D.M.W. Evaluation: From precision, recall and F­measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies. 2011;2(1):37–63. URL: https://bioinfopublication.org/fles/articles/2_1_1_JMLT.pdf (accessed 28.08.2018).</mixed-citation><mixed-citation xml:lang="en">Powers D.M.W. Evaluation: From precision, recall and F­measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies. 2011;2(1):37–63. URL: https://bioinfopublication.org/fles/articles/2_1_1_JMLT.pdf (accessed 28.08.2018).</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>
