A novel hybridization of artificial neural networks and ARIMA models for time series forecasting

By Mehdi Khashei, Mehdi Bijari. 2011

845 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jan Gasthaus
2. Tim Januschowski
3. Bernie Wang
4. Chih-Feng Liu
5. Henry Leung
6. Jun Zhao
7. King Fai Ma
8. Zhongyang Han

In Management Science and Operations Research

1. Bernie Wang
2. Tim Januschowski
3. Syama Sundar Rangapuram
4. Jan Gasthaus
5. Laurent Callot
6. Danielle C. Maddix
7. Sima Siami‐Namini
8. Akbar Siami Namin

Citations in the corpus

• Forecasting Economics and Financial Time Series: ARIMA vs. LSTM (2018, methodology): “Even though ARIMA models are very pervalent in modeling economical and financial time series [Banerjee 2005; Khashei and Bijari, 2011; Alonso and Garc´ıa-Martos, 2012; Adebiyi et al. 2014], they have some major limitations [Armstrong 2001; Earnest et al. 2005;].”
• Application of type-2 neuro-fuzzy modeling in stock price prediction (2012, methodology): “The given training data set is partitioned into clusters through input-similarity and output-similarity tests, and a type-2 TSK rule is derived from each cluster to form a fuzzy rule base.”
• Deep Learning for Time-Series Analysis (2017, methodology): “[31] presents a model for Time-Series forecasting using ANN and ARIMA models, and [15] applies the same kinds of models to water quality time series prediction.”
• Deep Learning Based Forecasting of Critical Infrastructure Data (2017, methodology): “One group of proposed methods is exclusively based on neural networks [4, 5], while other methods take advantage of ensemble techniques [12, 24, 27].”
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey (2020, methodology): “Zhang [201] MLP Point 1 MSE MSE, MAD sunspot, lynx, exchange rate Hybrid local model that uses ARIMA to capture the linear component and a NN for the nonlinear residuals Khashei and Bijari [100] MLP Point 1 MSE MAE, MSE sunspot, lynx, exchange rate Hybrid local model that uses ARIMA and a NN for tre”
• A Review of Deep Learning Models for Time Series Prediction (2019, background): “The problems are named as univariate [30] and multivariate [31], which are”
• A Comparison of ARIMA and LSTM in Forecasting Time Series (2018, background): “Even though ARIMA models are very prevalent in modeling economical and financial time series [1], [2], [14], they have some major limitations [6].”