A Comparison of ARIMA and LSTM in Forecasting Time Series
Сравнение ARIMA и LSTM при прогнозировании временных рядов
2018-12-01
SCID: 54.1/xgk3bdc4
Discuss with AI
ARIMA forecastingLong Short-Term Memorydeep learningforecast error ratestime series forecasting
Figures from the paper
Abstract (AI)
Forecasting time series data is an important subject in economics, business, and finance. Traditionally, there are several techniques to effectively forecast the next lag of time series data such as univariate Autoregressive (AR), univariate Moving Average (MA), Simple Exponential Smoothing (SES), and more notably Autoregressive Integrated Moving Average (ARIMA) with its many variations. In particular, ARIMA model has demonstrated its outperformance in precision and accuracy of predicting the next lags of time series. With the recent advancement in computational power of computers and more importantly development of more advanced machine learning algorithms and approaches such as deep learning, new algorithms are developed to analyze and forecast time series data. The research question investigated in this article is that whether and how the newly developed deep learning-based algorithms for forecasting time series data, such as "Long Short-Term Memory (LSTM)", are superior to the traditional algorithms. The empirical studies conducted and reported in this article show that deep learning-based algorithms such as LSTM outperform traditional-based algorithms such as ARIMA model. More specifically, the average reduction in error rates obtained by LSTM was between 84 - 87 percent when compared to ARIMA indicating the superiority of LSTM to ARIMA. Furthermore, it was noticed that the number of training times, known as "epoch" in deep learning, had no effect on the performance of the trained forecast model and it exhibited a truly random behavior.
Key Findings
1
Empirical results show that LSTM outperforms ARIMA in forecasting accuracy across the conducted studies.
2
LSTM reduces average forecasting error rates by 84–87% compared with ARIMA.
3
The number of LSTM training epochs had no apparent effect on forecast-model performance and showed truly random behavior.
4
The study compares traditional ARIMA forecasting with the deep learning-based Long Short-Term Memory (LSTM) approach for time series prediction.
Research Object
Time series data used for one-step-ahead forecasting
Research Subject
comparative forecasting performance and error rates of ARIMA and LSTM models, including the effect of training epochs
Publication Details
Publication Date
2018-12-01
Journal
Publisher
ISSN
Cited by
1520
Access Type
Author Information
Download PDF
Subscribe to digest