Review of Open-Source Libraries for Solving Time Series Forecasting Problems

91

Abstract

An overview of various open-source Python libraries for time series analysis and forecasting is presented. It covers such tools as Prophet, Kats, Merlion, as well as ARIMA, LSTM algorithms, which allow to study seasonality, trends and anomalies in time series data. The capabilities of each library, their advantages and applications in time series data analysis are discussed in detail.

General Information

Keywords: Python library, time series, open source, forecasting, trend, Prophet, Kats, Merlion

Journal rubric: Data Analysis

Article type: scientific article

DOI: https://doi.org/10.17759/mda.2024140203

Received: 08.04.2024

Accepted:

For citation: Svekolnikova E.A., Panovskiy V.N. Review of Open-Source Libraries for Solving Time Series Forecasting Problems. Modelirovanie i analiz dannikh = Modelling and Data Analysis, 2024. Vol. 14, no. 2, pp. 45–61. DOI: 10.17759/mda.2024140203. (In Russ., аbstr. in Engl.)

References

  1. Eileen Nielsen. Practical time series analysis: forecasting with statistics and machine learning.: Per. from English - St. Petersburg.: Dialectics, 2021. - 544 p.
  2. Box J., Jenkins G.M. Time series analysis, forecast and management. M.: Mir, 1974. 406 p.
  3. Vander Plas. Python for Complex Problems: Data Science and Machine Learning. - St. Petersburg: Peter, 2018. - 576 p.
  4. Alexey Chernobrovov. Top 7 Python libraries for time series analysis. URL: https://chernobrovov.ru/articles/top-7-python-bibliotek-dlya-vremennyh-ryadov.htm l. (Date of reference: 02.03.2024)
  5. G. Antipov, M.V. Fomina. The problem of anomaly detection in sets of time series. Program products and systems, No. 2 (98) 2012. - 168с. - с.78-82.
  6. Google Colab: [Electronic resource]. URL: https://colab.research.google.com/. (Date of reference: 04.03.2024)
  7. Kaggle: [Electronic resource]. URL: https://www.kaggle.com/. (Date of reference: 04.03.2024)
  8. NumPy: [Electronic resource]. URL: https://numpy.org/doc/. (Date of reference: 04.03.2024)
  9. Matplotlib: [Electronic resource]. URL: https://matplotlib.org/stable/index.html. (Date of reference: 04.03.2024)
  10. Seaborn: [Electronic resource]. URL: https://seaborn.pydata.org/. (Date of reference: 04.03.2024)
  11. Statsmodels: [Electronic resource]. URL: https://www.statsmodels.org/stable/index.html. (Date of reference: 04.03.2024)
  12. Prophet: [Electronic resource]. URL: https://prophet.readthedocs.io/en/latest/. (Date of access: 04.03.2024)
  13. Kats: [Electronic resource]. URL: https://kat.readthedocs.io/en/latest/. (Date of reference: 04.03.2024)
  14. Merlion: [Electronic resource]. URL: https://opensource.salesforce.com/Merlion/latest/index.html. (Date of reference: 04.03.2024)
  15. DeepAR Forecasting Algorithm: [Electronic resource]. URL: https://docs.aws.amazon.com/sagemaker/latest/dg/deepar.html. (Date of access: 04.03.2024)
  16. Python: [Electronic resource]. URL: https://www.python.org/ (Date of access: 04.03.2024)
  17. Pismarov A. V. To the question of prediction of the endurance limit of threaded parts with surface hardening // Trudy MAI. 2023. no. 129. URL: https://trudymai.ru/published.php?ID=173003
  18. Piganov M. N., Kulikov A. V., Novomeisky D. N. Predictional mathematical models of thin-film elements of microassembly // Trudy MAI. 2023. no. 131. URL: https://trudymai.ru/published.php?ID=175920
  19. Blinov A. V., Razumov D. A. The procedure of formalization of strategies as an element of the methodology for taking into account uncertainty factors in forecasting the indicators of the implementation of space technology development programs // Trudy MAI. 2022. no. 122. URL: https://trudymai.ru/published.php?ID=164270
  20. Belyaev B. V., Lebedev A. S. Methodology for predicting the residual resource during depressurization of aircraft // Trudy MAI. 2022. no. 125. URL: https://trudymai.ru/published.php?ID=168167

Information About the Authors

Elena A. Svekolnikova, Student, Department of Mathematical cybernetics, Moscow Aviation Institute (National Research University) (MAI), Moscow, Russia, ORCID: https://orcid.org/0009-0000-6161-571X, e-mail: elena.cvekolnikova@gmail.com

Valentin N. Panovskiy, PhD in Physics and Matematics, Associate Professor, Department of Mathematical Cybernetics, Moscow Aviation Institute (National Research University) (MAI), Moscow, Russia, ORCID: https://orcid.org/0009-0007-1708-8984, e-mail: panovskiy.v@yandex.ru

Metrics

Views

Total: 256
Previous month: 60
Current month: 25

Downloads

Total: 91
Previous month: 32
Current month: 6