Исследование влияния пандемии COVID-19 на международные авиаперевозки

Обложка

Цитировать

Полный текст

Аннотация

Прогнозирование временных рядов играет важную роль во многих областях исследований. Вследствие растущей доступности данных и вычислительных мощностей в последние годы глубокое обучение стало фундаментальной частью нового поколения моделей прогнозирования временных рядов, получающих отличные результаты.В данной работе представлены три различные архитектуры глубокого обучения для прогнозирования временных рядов: рекуррентные нейронные сети (RNN), которые являются наиболее известной и используемой архитектурой для задач прогнозирования временных рядов; долгая краткосрочная память (LSTM), которая представляет собой обобщённую и развитую РНС, разработанную для преодоления проблемы исчезающего градиента; закрытый рекуррентный блок (GRU), который является ещё одной эволюционной моделью РНС.Статья посвящена моделированию и прогнозированию стоимости международных авиаперевозок в условиях пандемии с использованием методов глубокого обучения и моделей рекуррентных сетей. В работе построены модели временных рядов цен акций American Airlines (AAL) с использованием моделей рекуррентных нейронных сетей LSTM, GRU, RNN и проведён сравнительный анализ результатов точности прогноза на выбранный период. Его результаты показали эффективность применения алгоритмов глубокого обучения для оценивания точности прогнозирования временных рядов.

Полный текст

Introduction In 2020, there was a significant drop in quotations of American Airlines (AAL) associated with the COVID-19 pandemic and a record-breaking de- crease in the number of air travel in the world. The generally accepted econometric methods of modeling and forecasting financial time series in these conditions turned out to be ineffective for making even short-term fore- casts [1], [2]. In the present paper, methods for modeling and forecasting international air traffic in the 2019-2020 pandemic are explored using recur- rent neural networks with different architectures. As an object of research, the day quotes of the American company AAL, traded on the NASDAQ ex- change, were selected; data from September 27, 2005 to September 30, 2020 from the information portal Yahoo Finance [3] were taken. The shares of this US company were selected due to its leading positions in the international air transportation market, high values of the trading turnover on the NASDAQ exchange, which in turn provides liquidity and shows investor interest in this exchange commodity [4]. Using the example of the value of AAL shares, we will try to build a reliable forecast using deep learning methods, in particular, recurrent neural networks [5]-[7]. Pre-processing of input data As input data for the neural network model, we will take a sequence consisting of the following values: Opent-1 - opening price for the previous period; Lowt-1 - the minimum price for the previous trading day; Hightt-1 - the maximum price for the previous trading day; Volumet-1 - the amount of shares sold and bought for the previous trading day; Closet-1 - closing price for the previous trading day. Based on the input data, neural networks will generate an output value that can be interpreted as the predicted value of the closing quotation today. For the correct operation of neural networks, it is necessary to normalize the data within the limits of [0 ∶ 1], as well as create training and test samples in the ratio 80:20 from the initial data having the dimension 3636. Thus, 2909 observations for the training sample and 727 observations for the test sample were obtained. The table 1 shows a fragment of the input data. It is necessary to remove the Date and Adj Close columns from the received data. The table 2 presents descriptive statistics of input data. It is seen that the average closing price is $27.13 and the standard deviation is $16.74. To study the statistical properties of the data further, let us build scatter diagrams of the profitability of the opening price and the closing price, as well as the profitability of the closing price shifted by one lag, and the closing price today. To calculate the profitability, we will use the following formula [8]- [10]:

×

Об авторах

Е. Ю. Щетинин

Финансовый университет при Правительстве Российской Федерации

Автор, ответственный за переписку.
Email: riviera-molto@mail.ru

Doctor of Physical and Mathematical Sciences, Lecturer of Department of Mathematics

Ленинградский проспект, д. 49, Москва, 125993, Россия

Список литературы

  1. J. D. A. Hamilton, The time series analysis. Princeton New Jersey: University Press, 1994.
  2. C. Brooks, Introductory econometrics for finance. Cambridge: Cambridge University Press, 2019.
  3. “American Airlines Group Inc. (AAL),” URL: https://finance.yahoo. com/quote/AAL/. Availabel: 2020-11-25, 2020.
  4. E. Y. Shchetinin, “On a structural approach to managing a company with high volatility of indicators [K analizu effektivnosti biznesa v usloviyah vysokoj izmenchivosti ego finansovyh aktivov],” Finansy i kredit, vol. 14, no. 218, pp. 39-41, 2006, [in Russian].
  5. J. Vander Plas, Python Data Science Handbook. Sebastopol, CA: O’Reilly Media, 2016.
  6. W. Richert and L. P. Coelho, Building Machine Learning Systems with Python. Birmingham: Packt, 2013.
  7. C. Bishop, Pattern recognition and machine learning. Berlin, Germany: Springer-Verlag, 2006.
  8. E. Y. Shchetinin, “Modeling the energy consumption of smart buildings using artificial intelligence,” in CEUR Workshop Proceedings, vol. 2407, 2019, pp. 130-140.
  9. M. Mudelsee, “Trend analysis of climate time series: A review of methods,” Earth-Science Reviews, vol. 190, pp. 310-322, 2019. DOI: 10.1016/ j.earscirev.2018.12.005.
  10. C. Chen, J. Twycross, and J. M. Garibaldi, “A new accuracy measure based on bounded relative error for time series forecasting,” PLOS ONE, vol. 12, no. 3, pp. 1-23, Mar. 2017. DOI: 10. 1371 / journal. pone. 0174202.
  11. R. J. Hyndman and G. Athanasopoulos, Forecasting: principles and practice. Melbourne, Australia: OTexts, 2018.
  12. A. Ghaderi, B. M. Sanandaji, and F. Ghaderi. “Deep forecast: deep learning-based spatio-temporal forecasting.” arXiv: 1707.08110 [cs.LG]. (2017).
  13. S. B. Taieb, A. Sorjamaa, and G. Bontempi, “Multiple-output modeling for multi-step-ahead time series forecasting,” Neurocomput, vol. 73, no. 10, pp. 1950-1957, 2010. doi: 10.1016/j.neucom.2009.11.030.
  14. R. Sen, H.-F. Yu, and I. S. Dhillon, “Think globally, act locally: a deep neural network approach to high-dimensional time series forecasting,” in Advances in neural information processing systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché-Buc, E. Fox, and R. Garnett, Eds., vol. 32, Curran Associates, Inc., 2019.
  15. “Keras,” URL: https://www.keras.io. Availabel: 2020-11-25, 2020.
  16. I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. Cambridge: The MIT Press, 2016.
  17. S. Galeshchuk and S. Mukherjee, “Deep networks for predicting direction of change in foreign exchange rates,” Intelligent Systems in Accounting, Finance and Management, vol. 24, no. 4, pp. 100-110, 2017. DOI: 10. 1002/isaf.1404.

Дополнительные файлы

Доп. файлы
Действие
1. JATS XML
Скачать

© Щетинин Е.Ю., 2021

Creative Commons License
Эта статья доступна по лицензии Creative Commons Attribution 4.0 International License.