QuantGplearn
Unverified ML strategy on Multi by WYFHHH. BotFinder score 18 out of 100.
Interpretable quantitative factor mining with genetic programming, NumPy/Pandas, and a Torch GPU panel backend.
Source: github
BotFinder analysis pending.
QuantGplearn
QuantGplearn Evolve interpretable quantitative factors. Evaluate them on CPU or GPU. Keep the formula. Quick start · Features · Operators · Architecture · Documentation --- QuantGplearn is a genetic-programming framework for quantitative factor research. Instead of fitting an opaque set of weights, it searches for human-readable expressions built from market features, rolling operators, and cross-sectional transformations: The same symbolic program representation can run through the original NumPy/Pandas engine or through a Torch tensor backend designed for dense panel data. The result is a practical bridge between explainable symbolic research and GPU-accelerated factor evaluation. QuantGplearn discovers candidate signals; it is not a promise of investment performance. Validate every factor with leakage-aware, out-of-sample research and a realistic execution model. 中文简介 QuantGplearn 是一个面向量化因子研究的遗传规划框架。它不输出难以解释的黑盒权重， 而是进化出由行情特征、时序算子和截面算子组成的可读公式。项目同时保留原有 NumPy/Pandas CPU 路径，并提供适用于 [时间, 标的, 特征] 面板数据的 Torch/GPU 执行后端，支持 IC、RankIC、ICIR 和多空组合 Sharpe 代理目标，以及因子相关性过滤。 Why QuantGplearn? | Capa
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)