MoTime: A Dataset Suite for Multimodal Time Series Forecasting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915312964730880 |
|---|---|
| author | Zhou, Xin Wang, Weiqing Baldán, Francisco J. Buntine, Wray Bergmeir, Christoph |
| author_facet | Zhou, Xin Wang, Weiqing Baldán, Francisco J. Buntine, Wray Bergmeir, Christoph |
| contents | While multimodal data sources are increasingly available from real-world forecasting, most existing research remains on unimodal time series. In this work, we present MoTime, a suite of multimodal time series forecasting datasets that pair temporal signals with external modalities such as text, metadata, and images. Covering diverse domains, MoTime supports structured evaluation of modality utility under two scenarios: 1) the common forecasting task, where varying-length history is available, and 2) cold-start forecasting, where no historical data is available. Experiments show that external modalities can improve forecasting performance in both scenarios, with particularly strong benefits for short series in some datasets, though the impact varies depending on data characteristics. By making datasets and findings publicly available, we aim to support more comprehensive and realistic benchmarks in future multimodal time series forecasting research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_15072 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoTime: A Dataset Suite for Multimodal Time Series Forecasting Zhou, Xin Wang, Weiqing Baldán, Francisco J. Buntine, Wray Bergmeir, Christoph Machine Learning Computation and Language Databases Information Retrieval While multimodal data sources are increasingly available from real-world forecasting, most existing research remains on unimodal time series. In this work, we present MoTime, a suite of multimodal time series forecasting datasets that pair temporal signals with external modalities such as text, metadata, and images. Covering diverse domains, MoTime supports structured evaluation of modality utility under two scenarios: 1) the common forecasting task, where varying-length history is available, and 2) cold-start forecasting, where no historical data is available. Experiments show that external modalities can improve forecasting performance in both scenarios, with particularly strong benefits for short series in some datasets, though the impact varies depending on data characteristics. By making datasets and findings publicly available, we aim to support more comprehensive and realistic benchmarks in future multimodal time series forecasting research. |
| title | MoTime: A Dataset Suite for Multimodal Time Series Forecasting |
| topic | Machine Learning Computation and Language Databases Information Retrieval |
| url | https://arxiv.org/abs/2505.15072 |