mlsanityData to 7 Oct 2026

Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions

arXiv 1909.00590 ↗First posted 2 Sep 2019cs.LG cs.NE stat.MLcited by 172

Not on the map. Why?

Abstract (arXiv)

Recurrent Neural Networks (RNN) have become competitive forecasting methods, as most notably shown in the winning method of the recent M4 competition. However, established statistical models such as ETS and ARIMA gain their popularity not only from their high accuracy, but they are also suitable for non-expert users as they are robust, efficient, and automatic. In these areas, RNNs have still a long way to go. We present an extensive empirical study and an open-source software framework of existing RNN architectures for forecasting, that allow us to develop guidelines and best practices for their use. For example, we conclude that RNNs are capable of modelling seasonality directly if the series in the dataset possess homogeneous seasonal patterns, otherwise we recommend a deseasonalization step. Comparisons against ETS and ARIMA demonstrate that the implemented (semi-)automatic RNN models are no silver bullets, but they are competitive alternatives in many situations.

Key facts. Cited by 172 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 31; 2023: 30; 2024: 33; 2025: 36; 2026: 25.

172 papers.

Sort:

By area:

  1. 2021Monash Time Series Forecasting Archivecited by 256
  2. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 234
  3. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  4. 2024TKAN: Temporal Kolmogorov-Arnold Networkscited by 70
  5. 2022Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practicescited by 54
  6. 2022Evaluation of post-hoc interpretability methods in time-series classificationcited by 53
  7. 2021An Experimental Review on Deep Learning Architectures for Time Series Forecastingcited by 47
  8. 2024From Similarity to Superiority: Channel Clustering for Time Series Forecastingcited by 37
  9. 2021Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologiescited by 34
  10. 2022A review of predictive uncertainty estimation with machine learningcited by 29
  11. 2024Unlocking the Power of LSTM for Long Term Time Series Forecastingcited by 29
  12. 2025Foundation Models for Time Series: A Surveycited by 19
38 more
  1. 2021A deep generative model for probabilistic energy forecasting in power systems: normalizing flowscited by 18
  2. 2024Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classificationcited by 18
  3. 2024BACKTIME: Backdoor Attacks on Multivariate Time Series Forecastingcited by 18
  4. 2022Robust Probabilistic Time Series Forecastingcited by 15
  5. 2024SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecastingcited by 15
  6. 2022Efficient Automated Deep Learning for Time Series Forecastingcited by 14
  7. 2021Variance Reduced Training with Stratified Sampling for Forecasting Modelscited by 13
  8. 2023GVFs in the Real World: Making Predictions Online for Water Treatmentcited by 13
  9. 2024xLSTMTime : Long-term Time Series Forecasting With xLSTMcited by 13
  10. 2022A review of machine learning concepts and methods for addressing challenges in probabilistic hydrological post-processing and forecastingcited by 12
  11. 2022W-Transformers : A Wavelet-based Transformer Framework for Univariate Time Series Forecastingcited by 12
  12. 2024ViTime: Foundation Model for Time Series Forecasting Powered by Vision Intelligencecited by 11
  13. 2025Diffusion Models for Time Series Forecasting: A Surveycited by 11
  14. 2026Reverso: Efficient Time Series Foundation Models for Zero-shot Forecastingcited by 11
  15. 2023Counterfactual Explanations for Time Series Forecastingcited by 10
  16. 2021MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Datacited by 9
  17. 2022Federated Learning based Energy Demand Prediction with Clustered Aggregationcited by 9
  18. 2024Weather-Informed Probabilistic Forecasting and Scenario Generation in Power Systemscited by 9
  19. 2021Parameter Efficient Deep Probabilistic Forecastingcited by 8
  20. 2021Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoMLcited by 7
  21. 2022A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacousticcited by 7
  22. 2022Learning Differential Operators for Interpretable Time Series Modelingcited by 7
  23. 2023It's All in the Embedding! Fake News Detection Using Document Embeddingscited by 7
  24. 2023A Comprehensive Survey on Generative Diffusion Models for Structured Datacited by 7
  25. 2021Boosted Embeddings for Time Series Forecastingcited by 6
  26. 2022LIMREF: Local Interpretable Model Agnostic Rule-based Explanations for Forecasting, with an Application to Electricity Smart Meter Datacited by 6
  27. 2022ES-dRNN with Dynamic Attention for Short-Term Load Forecastingcited by 6
  28. 2022Non-contrastive representation learning for intervals from well logscited by 6
  29. 2022Probabilistic Decomposition Transformer for Time Series Forecastingcited by 6
  30. 2023Staged Contact-Aware Global Human Motion Forecastingcited by 6
  31. 2024Gradient-Free Training of Recurrent Neural Networks using Random Perturbationscited by 6
  32. 2024Not All Frequencies Are Created Equal:Towards a Dynamic Fusion of Frequencies in Time-Series Forecastingcited by 6
  33. 2024Are KANs Effective for Multivariate Time Series Forecasting?cited by 6
  34. 2025S4M: S4 for multivariate time series forecasting with Missing valuescited by 6
  35. 2021Time Series Analysis and Modeling to Forecast: a Surveycited by 5
  36. 2022Bayesian Bilinear Neural Network for Predicting the Mid-price Dynamics in Limit-Order Book Marketscited by 5
  37. 2022Memory-free Online Change-point Detection: A Novel Neural Network Approachcited by 5
  38. 2023On Forecast Stabilitycited by 5

50 most cited of 172 All 172 (JSON)