Santa Fe
Institute
  • Research
    • Themes
    • Projects
    • SFI Press
    • Researchers
    • Publications
    • Library
    • Sponsored Research
    • Fellowships
    • Miller Scholarships
  • News + Events
    • News
    • Newsletters
    • Podcasts
    • SFI in the Media
    • Media Center
    • Events
    • Community
    • Journalism Fellowship
  • Education
    • Programs
    • Projects
    • Alumni
    • Complexity Explorer
    • Education FAQ
    • Postdoctoral Research
    • Education Supporters
  • People
    • Researchers
    • Fractal Faculty
    • Staff
    • Miller Scholars
    • Trustees
    • Governance
    • Resident Artists
    • Research Supporters
  • Applied Complexity
    • Office
    • Applied Projects
    • ACtioN
    • Applied Fellows
    • Studios
    • Applied Events
    • Login
  • Give
    • Give Now
    • Ways to Give
    • Contact
  • About
    • About SFI
    • Engage
    • Complex Systems
    • FAQ
    • Campuses
    • Jobs
    • Contact
    • Library
    • Employee Portal

Science for a Complex World

Events

Here's what's happening

Give

You make SFI possible

Subscribe

Sign up for research news

Connect

Follow us on social media

© 2026 Santa Fe Institute. All rights reserved. This site is supported by the Miller Omega Program.

Home / News

A simple baseline for AI forecasting in machine learning

Context parroting relies on short stretches of time-series data (or context). As it moves through the time series, it scans for similar patterns or motifs that appeared earlier in the sequence, and uses those patterns to predict what might come next. (Image: Yuanzhao Zhang & William Gilpin)
April 9, 2026

In a recent paper, SFI Complexity Postdoctoral Fellow Yuanzhao Zhang and co-author William Gilpin show that a deceptively simple forecasting strategy can outperform several leading machine learning forecasting models. 

Their method, called context parroting, relies on short stretches of time-series data. It works by comparing a short stretch of the time series with earlier parts of the same sequence, identifying similar patterns or motifs, and using what follows those earlier patterns to predict what might come next.

Researchers need to be careful when judging the performance and intelligence of AI systems and must keep working to open up the black box of how they make predictions, says Zhang, and this paper is a reminder about why. 

The paper’s three main contributions reinforce that message. First, it introduces context parroting as a strong and surprisingly effective baseline for zero-shot forecasting, which means predicting a new system from only a short stretch of data and no prior training on that specific system. Second, it shows that this simple approach can outperform current leading models on difficult prediction tasks such as chaotic systems dynamics. Finally, it explains why forecast accuracy improves as more context is provided, with the rate of improvement linked to the complexity of the system being predicted.

The paper will be presented at the International Conference on Learning Representations in Rio de Janeiro, Brazil, April 23–27.





Share
  • Sign Up For SFI News
News Media Contact

Santa Fe Institute

Office of Communications
news@santafe.edu
505-984-8800



  • Tags
  • SFI News Release


More SFI News

View All News

Why noise may be the key to understanding cell group patterns

Reinventing democracy before it breaks

Do deep learning models recognize 3D shapes in the same way humans do?

Upending assumptions about learning, inspired by an AI phenomenon

Looking at AGI through the lens of natural intelligence

A simple baseline for AI forecasting in machine learning

Constantino Tsallis to co-chair the 2027 Nobel Symposium on Statistical Mechanics

How novelty arrives: Review of “The Origins of the New”

Working group asks, what’s the benefit of a brain?

Measuring irreversibility in gene transcription

ACtioN Academy engages industry leaders on AI and complexity

Arguing for a complex adaptive power grid

Mark Newman Awarded 2026 SIAM John von Neumann Prize

Review: Nonesuch, by SFI Miller Scholar Francis Spufford

Laurent Hébert-Dufresne to receive Young Scientist Award

What does it mean to compute?

Reassessing the scientific method

SFI External Professor Santiago Elena elected to the American Academy of Microbiology

From cells to companies: Study shows how diversity scales within complex systems

SFI Press launches “The Economy as an Evolving Complex System IV”