Industrial and organizational psychologists depend on meta-analysis to synthesize research and guide evidence-based practice, but producing a new meta-analysis is slow, expensive, and labor intensive. This year’s SIOP Machine Learning (ML) Competition will determine if and to what extent AI can create a meta-analysis from raw papers.
Teams will compete to build an end-to-end pipeline that automates article coding for meta-analysis. Given a set of research articles and a research question, each pipeline must identify the relevant predictor–outcome relationship, extract reported effect sizes, convert them to a common metric, and output a single aggregated effect size per study. The results are intended to reveal how artificial intelligence can accelerate and support the meta-analytic process across psychology.
The competition runs from March 7 through April 11, 2026, with winners presenting at this year’s SIOP Annual Conference. The competition is open to all, no prior machine learning experience is required, and welcomes participants from both academia and industry.
Learn more and register on the 2026 SIOP Machine Learning Competition webpage.
This year’s competition is brought to you by Ivan Hernandez, Isaac Thompson, and Egyn Zhu.
Post Type
Source
Topic
2026 Annual Conference, Machine Learning
