keyword
multi-horizon forecasting
Multi-horizon forecasting is a time series prediction approach that estimates the future values of a target variable across multiple consecutive future time points rather than predicting only a single next step. This technique enables long-range planning and decision-making in domains such as supply chain management, energy load scheduling, and financial forecasting. Unlike one-step-ahead forecasting, multi-horizon models must account for accumulating uncertainty over time and often incorporate complex temporal dynamics. They frequently utilize multiple data streams, including historical observations, known future inputs like scheduled events or seasonal calendars, and static context features. Implementations range from classical statistical methods and recursive autoregressive models to modern deep learning architectures, such as sequence-to-sequence networks and attention mechanisms, designed to capture dependencies across the entire projection window.
2 items
Domain Adaptation for Time Series Forecasting via Attention Sharing
Xiaoyong Jin, Youngsuk Park, Danielle C. Maddix, Hao Wang, Yuyang Wang
Why you should read this
Proposes an end-to-end domain adaptation framework for time series forecasting that aligns shared attention queries and keys across data-rich and data-scarce domains while preserving domain-specific values to improve multi-horizon predictions.
Recently, deep neural networks have gained increasing popularity in the field of time series forecasting. A primary reason for their success is their ability to effectively capture complex temporal dynamics across multiple related time series. The advantages of these deep forecasters only start to emerge in the presence of a sufficient amount of data. This poses a challenge for typical forecasting problems in practice, where there is a limited number of time series or observations per time series, or both. To cope with this data scarcity issue, we propose a novel domain adaptation framework, Domain Adaptation Forecaster (DAF). DAF leverages statistical strengths from a relevant domain with abundant data samples (source) to improve the performance on the domain of interest with limited data (target). In particular, we use an attention-based shared module with a domain discriminator across domains and private modules for individual domains. We induce domain-invariant latent features (queries and keys) and retrain domain-specific features (values) simultaneously to enable joint training of forecasters on source and target domains. A main insight is that our design of aligning keys allows the target domain to leverage source time series even with different characteristics. Extensive experiments on various domains demonstrate that our proposed method outperforms state-of-the-art baselines on synthetic and real-world datasets, and ablation studies verify the effectiveness of our design choices.
Added
2026-10-01
Time-series forecasting with deep learning: a survey
Bryan Lim, Stefan Zohren
Why you should read this
Categorizes modern deep learning and hybrid statistical architectures for multi-horizon time series forecasting, providing a clear guide on how different models encode temporal dynamics for operational decision support.
Numerous deep learning architectures have been developed to accommodate the diversity of time series datasets across different domains. In this article, we survey common encoder and decoder designs used in both one-step-ahead and multi-horizon time series forecasting -- describing how temporal information is incorporated into predictions by each model. Next, we highlight recent developments in hybrid deep learning models, which combine well-studied statistical models with neural network components to improve pure methods in either category. Lastly, we outline some ways in which deep learning can also facilitate decision support with time series data.
Added
2026-09-18