An Experimental Review on Deep Learning Architectures for Time Series Forecasting

@article{LaraBentez2021AnER,
  title={An Experimental Review on Deep Learning Architectures for Time Series Forecasting},
  author={Pedro Lara-Ben{\'i}tez and Manuel Carranza-Garc{\'i}a and Jos{\'e} Crist{\'o}bal Riquelme Santos},
  journal={International journal of neural systems},
  year={2021},
  pages={
          2130001
        }
}
In recent years, deep learning techniques have outperformed traditional models in many machine learning tasks. Deep neural networks have successfully been applied to address time series forecasting problems, which is a very important topic in data mining. They have proved to be an effective solution given their capacity to automatically learn the temporal dependencies present in time series. However, selecting the most convenient type of deep neural network and its parametrization is a complex… 
An application of deep learning for exchange rate forecasting
TLDR
Although the three architectures generate more accurate predictions than the time-series models, the results vary considerably depending on the specific topology, highlighting the importance of properly configuring, implementing and selecting the different topologies.
Performance of Deep Learning models with transfer learning for multiple-step-ahead forecasts in monthly time series
TLDR
The results suggest that deep learning models based on TCN, LSTM, and CNN with transfer learning tend to surpass the performance prediction of other traditional methods.
A Novel Encoder-Decoder Model for Multivariate Time Series Forecasting
TLDR
A novel deep learning architecture based on the encoder-decoder framework is proposed for MTS forecasting and the convolutional structure and fully connected module are established in order to enhance the performance and the discriminative ability of the new MTS.
A data filling methodology for time series based on CNN and (Bi)LSTM neural networks
TLDR
Two DL models aimed at filling data gaps in the case of internal temperature time series obtained from monitored apartments located in Bolzano, Italy are developed based on the combination of Convolutional Neural Networks, Long Short-Term Memory Neural networks, and Bidirectional LSTMs.
A Comparative Analysis of Machine Learning and Grey Models
TLDR
This survey illustrates, and demonstrates related studies for significance of Grey Machine Learning (GML), which is capable of handling large datasets as well as small datasets for time series forecasting likely outcomes.
A comparative study of non-deep learning, deep learning, and ensemble learning methods for sunspot number prediction
TLDR
The proposed ensemble model XGBoost-DL, which uses XGBeost as a two-level nonlinear ensemble method to combine the deep learning models, achieves the best forecasting performance among all considered models and the NASA’s forecast.
Time Series Analysis and Modeling to Forecast: a Survey
TLDR
This survey strives to meet the need for a sufficiently broad spectrum of models while nonetheless offering substantial methodological developments, and describes three major linear parametric models, together with two nonlinear extensions, and present five categories of nonlinearParametric models.
Handling Massive Proportion of Missing Labels in Multivariate Long-Term Time Series Forecasting
TLDR
An two-step process where interpolation (using Gaussian Processes Regression (GPR) and domain knowledge from experts) and prediction model are separated to enable the integration of prior domain knowledge.
A Survey on Semi-parametric Machine Learning Technique for Time Series Forecasting
TLDR
A primer survey on the GML framework, a comprehensive overview of the existing semi-parametric machine learning techniques for time series forecasting, is provided for researchers.
Technology investigation on time series classification and prediction
TLDR
This study focuses on analyzing the technical development routes of time series classification and prediction algorithms, and discusses the performance and applications of these different methods from classical statistical methods, to neural network methods, and then to fuzzy modeling and transfer learning methods.
...
1
2
3
4
...

References

SHOWING 1-10 OF 121 REFERENCES
Multivariate Temporal Convolutional Network: A Deep Neural Networks Approach for Multivariate Time Series Forecasting
TLDR
In this article, Beijing PM2.5 and ISO-NE Dataset are analyzed by a novel Multivariate Temporal Convolution Network (M-TCN) model, which indicates significant improvement of prediction accuracy, robust and generalization of the model.
Dilated Convolutional Neural Networks for Time Series Forecasting
TLDR
A convolutional network is well suited to regression-type problems and is able to effectively learn dependencies in and between the series without the need for long historical time series, that it is a time-efficient and easy-to-implement alternative to recurrent-type networks, and that it tends to outperform linear and recurrent models.
Deep learning for time series classification: a review
TLDR
This article proposes the most exhaustive study of DNNs for TSC by training 8730 deep learning models on 97 time series datasets and provides an open source deep learning framework to the TSC community.
Layered Ensemble Architecture for Time Series Forecasting
TLDR
The proposed layered ensemble architecture (LEA) for TSF problems uses the appropriate lag and combines the best trained networks to construct the ensemble, indicating LEA emphasis on accuracy of the networks.
Deep Learning for Time-Series Analysis
TLDR
A review of the main Deep Learning techniques is presented, and some applications on Time-Series analysis are summaried, making it clear that Deep Learning has a lot to contribute to the field.
Temporal Convolutional Networks Applied to Energy-related Time Series Forecasting
TLDR
The proposed TCN-based deep learning model outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
TLDR
A novel deep learning framework, namely Long- and Short-term Time-series network (LSTNet), to address this open challenge of multivariate time series forecasting, using the Convolution Neural Network and the Recurrent Neural Network to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends.
...
1
2
3
4
5
...