Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanisms

In real-world time series forecasting, uncertainty and lack of reliable evaluation pose significant challenges. Notably, forecasting errors often arise from underfitting in-distribution data and failing to handle out-of-distribution inputs. To enhance model reliability, we introduce a dual rejection mechanism combining ambiguity and novelty rejection. Ambiguity rejection, using prediction error variance, allows the model to abstain under low confidence, assessed through historical error variance analysis without future ground truth. Novelty rejection, employing Variational Autoencoders and Mahalanobis distance, detects deviations from training data. This dual approach improves forecasting reliability in dynamic environments by reducing errors and adapting to data changes, advancing reliability in complex scenarios.

@article{feng2025_2503.19656,
  title={ Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanisms },
  author={ Ninghui Feng and Songning Lai and Xin Zhou and Jiayu Yang and Kunlong Feng and Zhenxiao Yin and Fobao Zhou and Zhangyi Hu and Yutao Yue and Yuxuan Liang and Boyu Wang and Hang Zhao },
  journal={arXiv preprint arXiv:2503.19656},
  year={ 2025 }
}