mlsanityData to 7 Oct 2026

Evaluation of deep learning models for multi-step ahead time series prediction

arXiv 2103.14250 ↗First posted 26 Mar 2021cs.LG cs.AIcited by 25

Not on the map. Why?

Abstract (arXiv)

Time series prediction with neural networks has been the focus of much research in the past few decades. Given the recent deep learning revolution, there has been much attention in using deep learning models for time series prediction, and hence it is important to evaluate their strengths and weaknesses. In this paper, we present an evaluation study that compares the performance of deep learning models for multi-step ahead time series prediction. The deep learning methods comprise simple recurrent neural networks, long short-term memory (LSTM) networks, bidirectional LSTM networks, encoder-decoder LSTM networks, and convolutional neural networks. We provide a further comparison with simple neural networks that use stochastic gradient descent and adaptive moment estimation (Adam) for training. We focus on univariate time series for multi-step-ahead prediction from benchmark time-series datasets and provide a further comparison of the results with related methods from the literature. The results show that the bidirectional and encoder-decoder LSTM network provides the best performance in accuracy for the given time series problems.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 15 of its 108 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

15 of 108 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  7. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  8. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  10. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  11. 2015Named Entity Recognition with Bidirectional LSTM-CNNscited by 201
  12. 2014Multi-Step-Ahead Time Series Prediction using Multiple-Output Support Vector Regressioncited by 17
3 more
  1. 2017Predictive State Recurrent Neural Networkscited by 14
  2. 2018Langevin-gradient parallel tempering for Bayesian neural learningcited by 14
  3. 2017Co-evolutionary multi-task learning for dynamic time series predictioncited by 3

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 6; 2024: 10; 2025: 7.

25 papers.

Sort:

By area:

  1. 2023Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streamscited by 13
  2. 2023Bayesian neural networks via MCMC: a Python-based tutorialcited by 8
  3. 2024Time-Series Classification for Dynamic Strategies in Multi-Step Forecastingcited by 5
  4. 2025Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Errorcited by 5
  5. 2022A case study of spatiotemporal forecasting techniques for weather forecastingcited by 3
  6. 2024A Self-organizing Interval Type-2 Fuzzy Neural Network for Multi-Step Time Series Predictioncited by 3
  7. 2024Review of deep learning models for crypto price prediction: implementation and evaluationcited by 2
  8. 2024Stratify: Unifying Multi-Step Forecasting Strategiescited by 2
  9. 2023Recursive deep learning framework for forecasting the decadal world economic outlookcited by 1
  10. 2023Blockchain Transaction Fee Forecasting: A Comparison of Machine Learning Methodscited by 1
  11. 2023Probabilistic load forecasting with Reservoir Computingcited by 1
  12. 2023Multi-timestep models for Model-based Reinforcement Learningcited by 1
13 more
  1. 2024A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learningcited by 1
  2. 2024Accelerating Flood Warnings by 10 Hours: The Power of River Network Topology in AI-enhanced Flood Forecastingcited by 1
  3. 2024A Generative Model Based Honeypot for Industrial OPC UA Communicationcited by 1
  4. 2024Quantile deep learning models for multi-step ahead time series predictioncited by 1
  5. 2024MAIDS: Malicious Agent Identification-based Data Security Model for Cloud Environmentscited by 1
  6. 2025Spatiotemporal deep learning models for detection of rapid intensification in cyclonescited by 1
  7. 2022MUSTACHE: Multi-Step-Ahead Predictions for Cache Evictioncited by 0
  8. 2024RACH Traffic Prediction in Massive Machine Type Communicationscited by 0
  9. 2025Differential Machine Learning for Time Series Predictioncited by 0
  10. 2025Yet Unnoticed in LSTM: Binary Tree Based Input Reordering, Weight Regularization, and Gate Nonlinearizationcited by 0
  11. 2025Improving accuracy in short mortality rate series: Exploring Multi-step Forecasting Approaches in Hybrid Systemscited by 0
  12. 2025Extreme value forecasting using relevance-based data augmentation with deep learning modelscited by 0
  13. 2025QDeepGR4J: Quantile-based ensemble of deep learning and GR4J hybrid rainfall-runoff models for extreme flow prediction with uncertainty quantificationcited by 0