{"name":"correlation","repo":"bhoult/correlation","url":"https://midorreal.com/project/bhoult-correlation","repository":"https://github.com/bhoult/correlation","description":"Do stock correlations predict the market? 66 pre-registered tests, the data, and a triple pendulum that explains why not.  If you have an idea you want me to try, submit it as a PR and I will test it and get back to you.","facts":{"license":{"value":"GPL-3.0","source":"https://github.com/bhoult/correlation","checked":"21 Nov 2026"},"language":{"value":"Python","source":"https://github.com/bhoult/correlation","checked":"21 Nov 2026"},"releases":{"value":"0","source":"https://github.com/bhoult/correlation/releases","checked":"20 Nov 2026"},"contributors":{"value":"1","source":"https://github.com/bhoult/correlation/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/bhoult/correlation","checked":"21 Nov 2026"}},"stars":191.0,"writeup":{"what_it_is":"A research repository that tests whether stock correlations can predict market moves, using 66 or more pre-registered experiments on US stock price data. It also includes a Rust-based desktop app (c2-gui) for measuring how stocks move together, with tools for portfolio checks, diversifiers, hedges, and groups.","audience":"Investors and researchers interested in stock correlation analysis and trading strategy testing","claims":[{"kind":"specific","claim":"Lagged correlations appear at the rate chance produces, so they do not predict later moves","excerpt":"Lagged correlations turn up at the rate chance produces, at every delay and move length tried","status":"not_checked"},{"kind":"specific","claim":"A full census of lagged correlations across US stocks runs in about 13 minutes on one desktop GPU","excerpt":"1.57 trillion correlations in about 13 minutes on one desktop GPU","status":"not_checked"},{"kind":"specific","claim":"The top diversifier cut portfolio volatility by 5.1% more than random choices in out-of-sample testing","excerpt":"The top diversifier cut a portfolio's volatility by 5.1% more than random choices","status":"not_checked"},{"kind":"specific","claim":"The dataset covers 13,349 stocks and funds with 28 million daily rows","excerpt":"Data: 13,349 stocks and funds, 28 million daily rows","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-14"},"why_now":null,"owner_supplied":null,"score":{"verdict":"mid","hype":42,"reality":19,"gap":24,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-21T22:54:00+00:00","text":"Repository created","source":"https://github.com/bhoult/correlation"}],"cite":"correlation is a GitHub project at https://github.com/bhoult/correlation written mainly in Python, described there as \"Do stock correlations predict the market? 66 pre-registered tests, the data, and a triple pendulum that explains why not.  If you have an idea you want me to try, submit it as a PR and I will test it and get back to you\".","attribution":"Data from Mid or Real, https://midorreal.com/project/bhoult-correlation, checked 22 November 2026. Attribution with a link is required.","still_real":null}