Repositorybhoult/correlationResearch
It clearly demonstrates the practical limits of mathematical market prediction while showcasing how modern AI tools can implement complex, compute-heavy pipelines.
The core hypothesis dates back over twenty years: if macroeconomic factors affect companies at different rates, lagging correlations might reveal predictable market ripples. However, evaluating the entire stock market across variable offset windows required roughly 1.5 trillion calculations, making comprehensive testing historically impractical on consumer hardware.
An initial Ruby proof-of-concept estimated 15 years of run time on a 24-core desktop, while an inline C implementation would have taken six months. Using Claude 5.5, the author rewrote the entire computation in Rust to fully utilize all CPU cores, the GPU, and the onboard NPU, drastically compressing execution time.
The project appeals to data scientists, quantitative analysts, and software developers interested in algorithmic trading limits. Distributed under the GPL-3.0 license, it stands as an empirical research project featuring 66 pre-registered tests. The author uses three identical triple pendulums to illustrate how sensitivity to initial conditions creates chaotic divergeance, invalidating simplistic correlation models.
Summary generated by AI (Gemini 3.8 Flash, 28 October 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Repository:ultraworkers/claw-code
Claw Code is an open-source Rust project configured as a self-sustaining museum exhibit, developed and maintained entirely without human intervention by AI agent harnesses.
195.2kstarsRust
Repository:coleam00/Archon
Archon is an open-source harness builder and workflow engine built on TypeScript and Bun that makes AI coding agents repeatable and deterministic using YAML workflows.
23.4kstarsTypeScript
Repository:anthropics/claude-cookbooks
Anthropic's claude-cookbooks repository provides practical code recipes and Jupyter notebooks designed to help developers build applications with the Claude API.
52.4kstarsJupyter Notebook
Repository:anthropics/knowledge-work-plugins
Anthropic has open-sourced eleven plugins designed to tailor Claude Cowork and Claude Code to specific professional roles. Each plugin bundles skills, connectors, slash commands, and sub-agents for distinct knowledge work functions.
23.9kstarsPython
Repository:alexeyban/EKOS
EKOS (Enterprise Knowledge Operating System) is an open-source Rust-based platform designed to observe, compile, and serve enterprise knowledge from disparate sources via the Model Context Protocol (MCP) for AI agents.
10starsRust
Repository:alexfazio/artificial-analysis-compare
A Python-based skill tool that queries the Artificial Analysis API to compare large language models such as GPT-5, Claude, and Gemini across benchmarks, pricing, and speed metrics.
12starsPython
Parts of this content were created with the assistance of AI.
