CUDA-accelerated quantitative research and backtesting for formulas, model signals and target positions across equities and crypto.
-
Updated
Nov 15, 2026 - Python
CUDA-accelerated quantitative research and backtesting for formulas, model signals and target positions across equities and crypto.
Family-aware evolutionary alpha mining with LLM-guided symbolic hybridization.
An agentic-AI, full-featured quant strategy builder — from a concept to a validated, trained and deployment-ready system: automated alpha mining, backtesting and falsification, and reinforcement-learning trading agents.
LLM-agent pipeline for formulaic alpha discovery on WorldQuant BRAIN, published with the full research archive it produced (archived)
Local-first Rust toolkit for quantitative expression search: typed genetic programming, semantic deduplication, feedback-guided search, and causal factor evaluation. Reproducible artifacts, no cloud required.
Diffusion-flow generative model for alpha factor discovery — learns P(α) ∝ R(α) over expression space for diverse, reward-proportional alpha portfolios
可审计的 Alpha 因子自动演化框架(技能图 + 治理闭环)
⚗️ LLM×GP 自动挖掘 Alpha 因子 + 手写防泄漏向量化回测引擎 | LLM & genetic-programming alpha mining with a hand-rolled leak-safe vectorized backtester
Studying how alpha-mining systems search: a fixed-evaluation-budget harness for formulaic alpha discovery
End-to-end Python implementation of He's (2026) audit pipeline for LLM factor-mining claims. Implements: hash-verified custody, anti-look-ahead feature/label separation, freeze-before-score cohorts, average-tie daily rank-IC, a three-state ledger that keeps every record in the denominator, a versioned v1-to-v2 evaluator fix and claim governance.
A股因子自进化与诚实验证方法论:8 类系统性证伪、652 次试验、预注册与观察单制度 | Self-evolving A-share factor engine with an honest-validation methodology: 8 falsification campaigns, 652 honestly-counted trials, pre-registration and frozen watchlists
LLM-driven alpha-factor mining with decay-resistant regularization, evaluated against WRDS CRSP equity data.
Wiki 增强的 LLM 因子挖掘系统 · 演示视频 — 输入研究方向自动完成挖掘→评估→改进,三槽知识注入 + 三道质量门
Natural-language guided factor mining, walk-forward evaluation, and paper replication with a web UI and CLI.
RL agent (MaskablePPO) that mines interpretable stock alpha formulas using peer-graph operators; walk-forward tested on Nifty 200.
To associate your repository with the alpha-mining topic, visit your repo's landing page and select "manage topics."