Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous Context

• URL: http://arxiv.org/abs/2609.15087v1
• Date: Mon, 14 Sep 2026 06:01:16 GMT
• Title: Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous Context
• Abstract summary: MUSE-Bench is a unified benchmark for multimodal time series forecasting with heterogeneous context.<n>It comprises fourteen datasets across eight domains and six types of context.
• Score: 10.330435945681916
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-world temporal dynamics. Existing multimodal benchmarks also suffer from limited data and context coverage, fragmented evaluation settings, and overreliance on aggregate evaluation. In this paper, we propose \textbf{MUSE-Bench}, a unified benchmark for multimodal time series forecasting with heterogeneous context. It comprises fourteen datasets across eight domains and six types of context: metadata, events, holidays, news, images, and numerical covariates. We evaluate diverse forecasting paradigms, including statistical, data-specific, foundation, multimodal, and general-purpose LLM forecasting methods under shared non-overlapping forecast windows, common target observations, and consistent point and probabilistic metrics. Extensive experiments yield three main findings. First, numerical time series foundation models dominate the overall ranking, while Aurora, the evaluated multimodal foundation model, trails the leading numerical TSFMs but outperforms all evaluated data-specific models. Second, ablations show that external context improves the four evaluated context-aware models, whereas incorrect or temporally misaligned context degrades performance. Third, general-purpose LLMs perform poorly as direct forecasters, and LLM-guided refinement does not yield consistent improvements. MUSE-Bench enables systematic evaluation of how forecasting models utilize context and provides a foundation for future multimodal forecasting research.

Related papers

• Nexus : An Agentic Framework for Time Series Forecasting [72.73790673303154]
  Time series forecasting requires reasoning with unstructured contextual data such as news or events.<n>We introduce Nexus, a multi-agent forecasting framework that decomposes prediction into specialized stages.<n>We show that current-generation LLMs possess substantially stronger intrinsic forecasting ability than previously recognized.
  arXiv  Detail & Related papers  (2026-05-14T05:12:13Z)
• It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks [87.7937890373758]
  Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.<n>We introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks.<n>We propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels.
  arXiv  Detail & Related papers  (2026-02-12T16:31:01Z)
• What If TSF: A Benchmark for Reframing Forecasting as Scenario-Guided Multimodal Forecasting [8.593646221015264]
  What If TSF (WIT) is a benchmark designed to evaluate whether models can condition their forecasts on contextual text.<n>WIT offers a rigorous testbed for scenario-guided multimodal forecasting.
  arXiv  Detail & Related papers  (2026-01-13T12:47:43Z)
• Time Series Foundation Models: Benchmarking Challenges and Requirements [0.0]
  Time Series Foundation Models (TSFMs) represent a new paradigm for time series forecasting.<n> evaluating TSFMs is tricky, as with ever more extensive training sets, it becomes more challenging to ensure integrity benchmarking data.
  arXiv  Detail & Related papers  (2025-10-15T15:15:45Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• When Does Multimodality Lead to Better Time Series Forecasting? [96.26052272121615]
  We investigate whether and under what conditions such multimodal integration consistently yields gains.<n>Our findings reveal that the benefits of multimodality are highly condition-dependent.<n>Our study offers a rigorous, quantitative foundation for understanding when multimodality can be expected to aid forecasting tasks.
  arXiv  Detail & Related papers  (2025-06-20T23:55:56Z)
• ModelRadar: Aspect-based Forecast Evaluation [0.393259574660092]
  Current practices for evaluating and comparing forecasting models focus on summarising performance into a single score.<n>This limitation is especially problematic for time series forecasting, where multiple layers of averaging--across time steps, horizons, and multiple time series in a dataset--can mask relevant performance variations.<n>We propose ModelRadar, a framework for evaluating univariate time series forecasting models across multiple aspects, such as stationarity, presence of anomalies, or forecasting horizons.
  arXiv  Detail & Related papers  (2025-03-31T11:50:45Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context.<n>We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters.<n>We propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• MECATS: Mixture-of-Experts for Quantile Forecasts of Aggregated Time Series [11.826510794042548]
  We introduce a mixture of heterogeneous experts framework called textttMECATS. It simultaneously forecasts the values of a set of time series that are related through an aggregation hierarchy. Different types of forecasting models can be employed as individual experts so that the form of each model can be tailored to the nature of the corresponding time series.
  arXiv  Detail & Related papers  (2021-12-22T05:05:30Z)
• Cluster-and-Conquer: A Framework For Time-Series Forecasting [94.63501563413725]
  We propose a three-stage framework for forecasting high-dimensional time-series data. Our framework is highly general, allowing for any time-series forecasting and clustering method to be used in each step. When instantiated with simple linear autoregressive models, we are able to achieve state-of-the-art results on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-26T20:41:19Z)

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.