Contrastive Time Series Forecasting with Anomalies

• URL: http://arxiv.org/abs/2512.11526v1
• Date: Fri, 12 Dec 2025 12:54:24 GMT
• Title: Contrastive Time Series Forecasting with Anomalies
• Authors: Joel Ekstrand, Zahra Taghiyarrenani, Slawomir Nowaczyk,
• Abstract summary: Time series forecasting predicts future values from past data.<n>Some anomalous events have lasting effects and influence the forecast, while others are short-lived and should be ignored.<n>We propose Co-TSFA (Contrastive Time Series Forecasting with Anomalies), a regularization framework that learns when to ignore anomalies and when to respond.
• Score: 3.4598718746610593
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Time series forecasting predicts future values from past data. In real-world settings, some anomalous events have lasting effects and influence the forecast, while others are short-lived and should be ignored. Standard forecasting models fail to make this distinction, often either overreacting to noise or missing persistent shifts. We propose Co-TSFA (Contrastive Time Series Forecasting with Anomalies), a regularization framework that learns when to ignore anomalies and when to respond. Co-TSFA generates input-only and input-output augmentations to model forecast-irrelevant and forecast-relevant anomalies, and introduces a latent-output alignment loss that ties representation changes to forecast changes. This encourages invariance to irrelevant perturbations while preserving sensitivity to meaningful distributional shifts. Experiments on the Traffic and Electricity benchmarks, as well as on a real-world cash-demand dataset, demonstrate that Co-TSFA improves performance under anomalous conditions while maintaining accuracy on normal data. An anonymized GitHub repository with the implementation of Co-TSFA is provided and will be made public upon acceptance.

Related papers

• Test-Time Adaptation for Non-stationary Time Series: From Synthetic Regime Shifts to Financial Markets [0.0]
  We study a small-footprint test-time adaptation framework for causal timeseries forecasting and direction classification.<n>For classification we minimize entropy and enforce temporal consistency; for regression we minimize prediction variance across weak time-preserving augmentations.<n>We evaluate this framework in two stages: synthetic regime shifts on ETT benchmarks, and daily equity and FX series (SPY, QQQ, EUR/USD) across pandemic, high-inflation, and recovery regimes.
  arXiv  Detail & Related papers  (2026-01-20T22:30:23Z)
• Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecasting [3.769861522138544]
  We propose Weighted Contrastive Adaptation (WECA), a weighted contrastive objective that aligns normal and anomaly-augmented representations.<n>We evaluate WECA on a nationwide ATM transaction dataset with domain-informed anomaly injection.
  arXiv  Detail & Related papers  (2025-12-08T14:02:31Z)
• Beyond MSE: Ordinal Cross-Entropy for Probabilistic Time Series Forecasting [11.320830769077027]
  Current deep learning-based forecasting models primarily employ Mean Squared Error (MSE) loss functions for regression modeling.<n>We propose OCE-TS, a novel ordinal classification approach for time series forecasting that replaces MSE with Ordinal Cross-Entropy (OCE) loss.<n>Using MSE and Mean Absolute Error (MAE) as evaluation metrics, the results demonstrate that OCE-TS consistently outperforms benchmark models.
  arXiv  Detail & Related papers  (2025-11-13T11:14:24Z)
• Forecast2Anomaly (F2A): Adapting Multivariate Time Series Foundation Models for Anomaly Prediction [4.113311437158182]
  We present Forecast2Anomaly (F2A), a novel framework that empowers TSFMs with anomaly prediction abilities.<n>First, we propose a joint forecast-anomaly loss that fine-tunes TSFMs to accurately forecast future signals even at anomalous time points.<n>Second, we introduce a Retrieval-Augmented Generation (RAG) module that retrieves historically relevant horizons and conditions predictions on them.
  arXiv  Detail & Related papers  (2025-11-05T03:13:26Z)
• DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment [92.70019102733453]
  Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence.<n>We propose DistDF, which achieves alignment by alternatively minimizing a discrepancy between the conditional forecast and label distributions.
  arXiv  Detail & Related papers  (2025-10-28T16:09:59Z)
• Predictive inference for time series: why is split conformal effective despite temporal dependence? [8.032656343027146]
  Conformal prediction methods provide distribution-free coverage for any iid or exchangeable data distribution.<n>Using predictors with "memory" -- i.e., predictors that utilize past observations, such as autoregressive models -- further exacerbates this problem.<n>Our results bound the loss of coverage of these methods in terms of a new "switch coefficient", measuring the extent to which temporal dependence within the time series creates violations of exchangeability.
  arXiv  Detail & Related papers  (2025-10-02T18:24:04Z)
• Error-quantified Conformal Inference for Time Series [55.11926160774831]
  Uncertainty quantification in time series prediction is challenging due to the temporal dependence and distribution shift on sequential data.<n>We propose itError-quantified Conformal Inference (ECI) by smoothing the quantile loss function.<n>ECI can achieve valid miscoverage control and output tighter prediction sets than other baselines.
  arXiv  Detail & Related papers  (2025-02-02T15:02:36Z)
• Stock Volume Forecasting with Advanced Information by Conditional Variational Auto-Encoder [49.97673761305336]
  We demonstrate the use of Conditional Variational (CVAE) to improve the forecasts of daily stock volume time series in both short and long term forecasting tasks. CVAE generates non-linear time series as out-of-sample forecasts, which have better accuracy and closer fit of correlation to the actual data.
  arXiv  Detail & Related papers  (2024-06-19T13:13:06Z)
• Enhancing Mean-Reverting Time Series Prediction with Gaussian Processes: Functional and Augmented Data Structures in Financial Forecasting [0.0]
  We explore the application of Gaussian Processes (GPs) for predicting mean-reverting time series with an underlying structure. GPs offer the potential to forecast not just the average prediction but the entire probability distribution over a future trajectory. This is particularly beneficial in financial contexts, where accurate predictions alone may not suffice if incorrect volatility assessments lead to capital losses.
  arXiv  Detail & Related papers  (2024-02-23T06:09:45Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2023-10-17T20:30:16Z)
• Performative Time-Series Forecasting [64.03865043422597]
  We formalize performative time-series forecasting (PeTS) from a machine-learning perspective.<n>We propose a novel approach, Feature Performative-Shifting (FPS), which leverages the concept of delayed response to anticipate distribution shifts.<n>We conduct comprehensive experiments using multiple time-series models on COVID-19 and traffic forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-09T18:34:29Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2022-06-16T06:13:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.