RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models

2026-07-07 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Expert, quick

Summary

The RMISC corpus is introduced as a large-scale, high-quality, openly accessible, real-world multivariate time series archive. This corpus comprises approximately 200 datasets and 142 billion time points spanning various domains, addressing the limitations of synthetic data often used for pretraining time series foundation models (TSFMs). Researchers pretrained four advanced TSFMs using univariate, synthetic multivariate, and real-world multivariate data to assess the impact of real-world data on zero-shot generalization. Experimental results consistently demonstrate that incorporating real-world multivariate data significantly enhances the generalization performance for both univariate and multivariate TSFMs, offering crucial insights into developing more robust TSFMs.

Key takeaway

For Machine Learning Engineers developing Time Series Foundation Models, you should prioritize real-world multivariate datasets like RMISC for pretraining. Your models will achieve superior zero-shot generalization compared to those trained solely on synthetic data, especially when facing out-of-distribution challenges. Incorporating such high-quality, diverse real-world data is critical for building robust and adaptable TSFMs.

Key insights

Pretraining time series foundation models with real-world multivariate data significantly improves zero-shot generalization.

Principles

• Real-world data captures complex temporal dynamics.
• Synthetic data may lack real-world relationships.
• Multivariate real-world data enhances TSFM generalization.

Method

Pretrain TSFMs on univariate, synthetic multivariate, and real-world multivariate data, then evaluate zero-shot generalization on in-distribution and out-of-distribution benchmarks.

In practice

• Utilize RMISC for TSFM pretraining.
• Prioritize real-world over synthetic data.
• Evaluate TSFMs on diverse benchmarks.

Topics

• Time Series Foundation Models
• Multivariate Time Series
• Real-world Datasets
• Zero-shot Generalization
• RMISC Corpus
• Pretraining Data

Best for: Research Scientist, AI Scientist, Machine Learning Engineer

Related on AIssential

• TTM: Tiny Foundation Models for Multivariate Time-Series Forecasting — Tiny Time Mixers (TTMs) enable efficient, accurate time-series forecasting via compact pre-trained models and multi-level adaptation.
• Zero-shot Multivariate Time Series Forecasting Using Tabular Prior Fitted Networks — Multivariate time series forecasting can be reframed as scalar regression for zero-shot tabular foundation model application.
• Five Questions About Chronos-2, the Time Series Foundation Model — Time series foundation models like Chronos-2 enable zero-shot forecasting by learning recurring temporal shapes from diverse data.
• The digital quant: instant portfolio optimization with JointFM — JointFM is a zero-shot foundation model predicting full multivariate distributions for instant, domain-agnostic time-series forecasting.
• Interview with AAAI Fellow Yan Liu: machine learning for time series — Physics-informed foundation models enable accurate, adaptable time series analysis, especially in data-scarce scientific and real-world applications.
• Data Machina #261 — Generative AI and LLMs are being adapted to achieve state-of-the-art performance in diverse time-series tasks.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.