mlsanityData to 7 Oct 2026

Historical Inertia: A Neglected but Powerful Baseline for Long Sequence Time-series Forecasting

arXiv 2103.16349 ↗First posted 30 Mar 2021cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

Long sequence time-series forecasting (LSTF) has become increasingly popular for its wide range of applications. Though superior models have been proposed to enhance the prediction effectiveness and efficiency, it is reckless to neglect or underestimate one of the most natural and basic temporal properties of time-series. In this paper, we introduce a new baseline for LSTF, the historical inertia (HI), which refers to the most recent historical data-points in the input time series. We experimentally evaluate the power of historical inertia on four public real-word datasets. The results demonstrate that up to 82% relative improvement over state-of-the-art works can be achieved even by adopting HI directly as output.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 10 of its 14 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

10 of 14 references.

References · 10

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2020Reformer: The Efficient Transformercited by 1,658
  5. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  6. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  7. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  8. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  9. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  10. 2018Automated Machine Learning: From Principles to Practicescited by 62

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 5; 2024: 10; 2025: 5; 2026: 4.

26 papers.

Sort:

By area:

  1. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 149
  2. 2022Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practicescited by 54
  3. 2023ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecastingcited by 21
  4. 2024Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecastingcited by 18
  5. 2023HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecastingcited by 12
  6. 2023STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecastingcited by 12
  7. 2023A Systematic Review for Transformer-based Long-term Series Forecastingcited by 10
  8. 2023Dynamic Frequency Domain Graph Convolutional Network for Traffic Forecastingcited by 10
  9. 2024SpoT-Mamba: Learning Long-Range Dependency on Spatio-Temporal Graphs with Selective State Spacescited by 7
  10. 2024On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecastingcited by 7
  11. 2024EasyST: A Simple Framework for Spatio-Temporal Predictioncited by 6
  12. 2025Dynamic Trend Fusion Module for Traffic Flow Predictioncited by 5
14 more
  1. 2025How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learningcited by 4
  2. 2024STLLM-DF: A Spatial-Temporal Large Language Model with Diffusion for Enhanced Multi-Mode Traffic System Forecastingcited by 3
  3. 2024ST-MambaSync: The Complement of Mamba and Transformers for Spatial-Temporal in Traffic Flow Predictioncited by 2
  4. 2024RePST: Language Model Empowered Spatio-Temporal Forecasting via Semantic-Oriented Reprogrammingcited by 2
  5. 2025A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Predictioncited by 2
  6. 2024ST-Mamba: Spatial-Temporal Selective State Space Model for Traffic Flow Predictioncited by 1
  7. 2024Multiscale Spatio-Temporal Enhanced Short-term Load Forecasting of Electric Vehicle Charging Stationscited by 1
  8. 2025ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecastingcited by 1
  9. 2026UrbanFM: Scaling Urban Spatio-Temporal Foundation Modelscited by 1
  10. 2024Linear Attention is Enough in Spatial-Temporal Forecastingcited by 0
  11. 2025Channel-Independent Federated Traffic Predictioncited by 0
  12. 2026DWAFM: Dynamic Weighted Graph Structure Embedding Integrated with Attention and Frequency-Domain MLPs for Traffic Forecastingcited by 0
  13. 2026TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecastingcited by 0
  14. 2026AdaST: Adaptive Coupling for Spatial-Temporal Forecastingcited by 0