来自驾驶舱的现场笔记。

StratCraft 期刊 · 第 062 期 · 2026年11月

来自构建 StratCraft 引擎团队和在其上部署实盘策略的交易员的研究日志、事后复盘和工程深度分析。

精选 · 长文

INSIGHTS2026年5月25日阅读 8 min

ML vs LLM as Signal Generators: Eight Dimensions Where the Choice Is Already Made

ML vs LLM as a trading signal generator, broken down across eight dimensions: cost shape, failure mode, reproducibility, interpretability, and the one row where the LLM actually wins.

StratCraft

StratCraft 团队

阅读文章 →

本周阅读清单。

由团队精心挑选。来自互联网其他地方的研究、论文和报告。

5月25日insights

ML vs LLM as Signal Generators: Eight Dimensions Where the Choice Is Already Made

ML vs LLM as a trading signal generator, broken down across eight dimensions: cost shape, failure mode, reproducibility, interpretability, and the one row where the LLM actually wins.

StratCraft · 8 min

5月15日insights

I Asked an LLM to Generate 20 Trading Strategies. 14 Were the Same Thing.

After generating 20 LLM trading strategies, 14 reused the same mean-reversion shape. Here is what breaks when AI skips the validation stack.

StratCraft · 8 min

Start With an Evidence-Producing Research Loop

Use Community AI Studio with direct BYOK or a supported local model, then validate and backtest locally.

免费下载 →查看文档

产品

生态系统

交易

资源

来自驾驶舱的现场笔记。

ML vs LLM as Signal Generators: Eight Dimensions Where the Choice Is Already Made

最新报告。

I Asked an LLM to Generate 20 Trading Strategies. 14 Were the Same Thing.

本周阅读清单。

ML vs LLM as Signal Generators: Eight Dimensions Where the Choice Is Already Made

I Asked an LLM to Generate 20 Trading Strategies. 14 Were the Same Thing.

Start With an Evidence-Producing Research Loop

来自驾驶舱的现场笔记。

ML vs LLM as Signal Generators: Eight Dimensions Where the Choice Is Already Made

最新报告。

I Asked an LLM to Generate 20 Trading Strategies. 14 Were the Same Thing.

本周阅读清单。

ML vs LLM as Signal Generators: Eight Dimensions Where the Choice Is Already Made

I Asked an LLM to Generate 20 Trading Strategies. 14 Were the Same Thing.

每周五一封用心之邮。

Start With an Evidence-Producing Research Loop