Intervention-Aware Forecasting: Breaking Historical Limits from a System Perspective (2405.13522v3)
Abstract: Traditional time series forecasting methods predominantly rely on historical data patterns, neglecting external interventions that significantly shape future dynamics. Through control-theoretic analysis, we show that the implicit "self-stimulation" assumption limits the accuracy of these forecasts. To overcome this limitation, we propose an Intervention-Aware Time Series Forecasting (IATSF) framework explicitly designed to incorporate external interventions. We particularly emphasize textual interventions due to their unique capability to represent qualitative or uncertain influences inadequately captured by conventional exogenous variables. We propose a leak-free benchmark composed of temporally synchronized textual intervention data across synthetic and real-world scenarios. To rigorously evaluate IATSF, we develop FIATS, a lightweight forecasting model that integrates textual interventions through Channel-Aware Adaptive Sensitivity Modeling (CASM) and Channel-Aware Parameter Sharing (CAPS) mechanisms, enabling the model to adjust its sensitivity to interventions and historical data in a channel-specific manner. Extensive empirical evaluations confirm that FIATS surpasses state-of-the-art methods, highlighting that forecasting improvements stem explicitly from modeling external interventions rather than increased model complexity alone.
- Time series analysis: forecasting and control. John Wiley & Sons, 2015.
- Time-llm: Time series forecasting by reprogramming large language models. arXiv preprint arXiv:2310.01728, 2023.
- Reversible instance normalization for accurate time-series forecasting against distribution shift. In International Conference on Learning Representations, 2021. URL https://openreview.net/forum?id=cGDAkQo1C0p.
- Learning to embed time series patches independently. arXiv preprint arXiv:2312.16427, 2023.
- Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4):1748–1764, 2021.
- itransformer: Inverted transformers are effective for time series forecasting. arXiv preprint arXiv:2310.06625, 2023.
- A time series is worth 64 words: Long-term forecasting with transformers. In International Conference on Learning Representations, 2023.
- An analysis of linear time series forecasting models. arXiv preprint arXiv:2403.14587, 2024.
- Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023.
- Timexer: Empowering transformers for time series forecasting with exogenous variables. arXiv preprint arXiv:2402.19072, 2024.
- Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems, 34:22419–22430, 2021.
- Timesnet: Temporal 2d-variation modeling for general time series analysis. In International Conference on Learning Representations, 2023.
- Fits: Modeling time series with 10k10𝑘10k10 italic_k parameters. arXiv preprint arXiv:2307.03756, 2023.
- Are transformers effective for time series forecasting? 2023.
- Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp. 11106–11115, 2021.
- Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International Conference on Machine Learning, 2022a.
- FiLM: Frequency improved legendre memory model for long-term time series forecasting. In Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (eds.), Advances in Neural Information Processing Systems, 2022b. URL https://openreview.net/forum?id=zTQdHSQUQWc.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.