The paper proposes methodologies to measure lag relevance in machine learning forecasting models using Ghost variables, Shapley values, and additive importance measures. It also introduces auto-releva…

The paper introduces an LLM-agent framework to solve the 'last-mile forecasting' problem, bridging the gap between raw statistical predictions and business-ready forecasts by incorporating weakly stru…

The paper argues that long context windows are necessary for time series forecasting not just to capture long-range dependencies, but primarily to reduce uncertainty about the underlying data-generati…

The paper proposes INTARG, an informed and selective adversarial attack framework for time-series forecasting that significantly increases prediction error by targeting only the most vulnerable time s…

KairosAgent is a novel agentic framework that combines Large Language Models (LLMs) for semantic reasoning and Time Series Foundation Models (TSFMs) for numerical forecasting, achieving superior multi…

This paper introduces EVOTS, an evolutionary neural architecture search framework for discovering task-adaptive Transformer-like models for multivariate time-series forecasting.

The paper introduces QuITE, a plug-and-play embedding module that uses learnable query tokens to effectively embed irregular multivariate time series data into latent representations compatible with e…

This paper proposes Spiking Fourier Graph Operators (SpikF-GO) for multivariate time series forecasting using Spiking Neural Networks (SNNs), introducing Hard Concrete frequency gates and Complex LIF…

FreqLite introduces an ultra-lightweight, frequency-decomposed linear model that significantly outperforms complex transformers on long-term time-series forecasting while drastically reducing computat…

The paper proposes K-line--Quantile Sequential Projection (KQSP), a method to reconcile quantile and K-line crossing inconsistencies in probabilistic K-line forecasting without reordering, specialized…

ChronosAD introduces a novel architecture that uses time series foundation models and a custom Temporal Block to achieve robust and highly accurate anomaly detection across diverse domains.

The paper proposes Under-Cali, an uncertainty-driven dual-expert calibration framework, to achieve stable and efficient online forecasting for irregularly sampled multivariate time series.

This study proposes a hybrid Gaussian Process Regression and Holt-Winters smoothing framework to accurately forecast under-five malaria admissions in Ghana, achieving high predictive accuracy and prov…

The paper introduces Dr-CiK, a new benchmark designed to evaluate agents' ability to proactively discover, filter, and utilize relevant external context for time series forecasting, demonstrating that…

The paper proposes a novel nonparametric mutual information estimator to robustly quantify dependence between heterogeneous temporal data, specifically continuous time series and discrete event sequen…

This paper compares traditional machine learning models (Random Forests, XGBoost, SVM) against a complex Unified Multi-Task Time Series Model for churn prediction, concluding that conventional methods…

This paper proposes a behaviour-conditioned Attentive Neural Process framework for residential short-term load forecasting, using behavioural structure as conditioning signals.

This paper establishes the identifiability of latent regimes and regime-dependent causal structures in complex non-stationary time series modeled by Markov Switching Models, even with instantaneous ef…

The paper introduces EvoXXLTraffic, an ultra-large, sensor-evolving dataset that simulates real-world road network growth, demonstrating that existing state-of-the-art traffic forecasting models fail…