МОДЕЛЮВАННЯ ARIMA ТА LSTM МОДЕЛЕЙ ЧАСОВИХ РЯДІВ В PYTHON

Iryna Doroshenko; Maksym Tarasov

doi:10.30888/2663-5712.2025-30-01-003

MODELING ARIMA AND LSTM TIME SERIES MODELS IN PYTHON

Authors

Iryna Doroshenko Chernivtsi National University http://orcid.org/0000-0001-8729-1768
Maksym Tarasov Chernivtsi National University http://orcid.org/

DOI:

https://doi.org/10.30888/2663-5712.2025-30-01-003

Keywords:

time series analysis, machine learning, neural networks

Abstract

This article examines the theoretical foundations and practical aspects of applying ARIMA models, RNN architecture, and the working principles of LSTM, as well as their use for time series forecasting in Python using the Statsmodels and Keras libraries.

Metrics

PDF views

References

Тарасов М. С. Порівняння ARIMA та LSTM моделей часових рядів / Кваліфікаційна робота.- ЧНУ. – 2024. – 66 с.

Brownlee J. Introduction to Time Series Forecasting with Python. — 1st ed. — 2020. — 365 p.

Downloads

Published

2025-03-30

How to Cite

Дорошенко, І., & Тарасов, М. (2025). MODELING ARIMA AND LSTM TIME SERIES MODELS IN PYTHON. SWorldJournal, 1(30-01), 72–81. https://doi.org/10.30888/2663-5712.2025-30-01-003