Deep Learning for Time Series Forecasting: A Survey
arXiv:2503.10198 · doi:10.1007/s13042-025-02560-w
Abstract
Time series forecasting (TSF) has long been a crucial task in both industry and daily life. Most classical statistical models may have certain limitations when applied to practical scenarios in fields such as energy, healthcare, traffic, meteorology, and economics, especially when high accuracy is required. With the continuous development of deep learning, numerous new models have emerged in the field of time series forecasting in recent years. However, existing surveys have not provided a unified summary of the wide range of model architectures in this field, nor have they given detailed summaries of works in feature extraction and datasets. To address this gap, in this review, we comprehensively study the previous works and summarize the general paradigms of Deep Time Series Forecasting (DTSF) in terms of model architectures. Besides, we take an innovative approach by focusing on the composition of time series and systematically explain important feature extraction methods. Additionally, we provide an overall compilation of datasets from various domains in existing works. Finally, we systematically emphasize the significant challenges faced and future research directions in this field.
References in corpus (18)
- Challenges of Big Data Analysis
- Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
- Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
- Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting
- TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting
- Electrical Load Forecasting Using Edge Computing and Federated Learning
- LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns
- Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification
- Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
- CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection
- Self-supervised Learning for ECG-based Emotion Recognition
- Benchmark Dataset for Mid-Price Forecasting of Limit Order Book Data with Machine Learning Methods
- TSViz: Demystification of Deep Learning Models for Time-Series Analysis
- Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGAN
- SageFormer: Series-Aware Framework for Long-term Multivariate Time Series Forecasting
- Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems
- Explainable Tensorized Neural Ordinary Differential Equations forArbitrary-step Time Series Prediction
- CasCIFF: A Cross-Domain Information Fusion Framework Tailored for Cascade Prediction in Social Networks