An Experimental Review on Deep Learning Architectures for Time Series Forecasting

Abstract

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 task that requires considerable expertise. Therefore, there is a need for deeper studies on the suitability of all existing architectures for different forecasting tasks. In this work, we face two main challenges: a comprehensive review of the latest works using deep learning for time series forecasting; and an experimental study comparing the performance of the most popular architectures. The comparison involves a thorough analysis of seven types of deep learning models in terms of accuracy and efficiency. We evaluate the rankings and distribution of results obtained with the proposed models under many different architecture configurations and training hyperparameters. The datasets used comprise more than 50000 time series divided into 12 different forecasting problems. By training more than 38000 models on these data, we provide the most extensive deep learning study for time series forecasting. Among all studied models, the results show that long short-term memory (LSTM) and convolutional networks (CNN) are the best alternatives, with LSTMs obtaining the most accurate forecasts. CNNs achieve comparable performance with less variability of results under different parameter configurations, while also being more efficient.

References in corpus (2)

• Deep learning for time series classification: a review
• Light Gated Recurrent Units for Speech Recognition

Cited by in corpus (17)

• Deep learning models for price forecasting of financial time series: A review of recent advancements: 2020-2022
• IoT Data Analytics in Dynamic Environments: From An Automated Machine Learning Perspective
• Federated Learning for 5G Base Station Traffic Forecasting
• Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends
• Deep Learning Based Forecasting of Indian Summer Monsoon Rainfall
• Time-Series Forecasting in Smart Manufacturing Systems: An Experimental Evaluation of the State-of-the-art Algorithms
• 1D-CapsNet-LSTM: A Deep Learning-Based Model for Multi-Step Stock Index Forecasting
• Human Silhouette and Skeleton Video Synthesis through Wi-Fi signals
• Mamba time series forecasting with uncertainty quantification
• RSSi-based visitor tracking in museums via cascaded AI classifiers and coloured graph representations
• Improving Long-term Autoregressive Spatiotemporal Predictions: A Proof of Concept with Fluid Dynamics
• Comparison of neural network architectures for feature extraction from binary black hole merger waveforms
• Salt-Rock Creep Deformation Forecasting Using Deep Neural Networks and Analytical Models for Subsurface Energy Storage Applications
• Energy Efficient LSTM Accelerators for Embedded FPGAs through Parameterised Architecture Design
• A comparative study of non-deep learning, deep learning, and ensemble learning methods for sunspot number prediction
• Persistent homology of featured time series data and its applications
• Quantum dynamics evolution predicted by the long short-term memory network in the photosystem II reaction center