# QuantML

**Repository Path**: thomastao/QuantML

## Basic Information

- **Project Name**: QuantML
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-08-13
- **Last Updated**: 2025-08-13

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# 机器学习&量化学术交流


本项目目前包括：


## **MODEL ZOO**

[MODEL ZOO 结果](https://github.com/chaosquant2022/ML-Quant/tree/main/model_zoo)

<BR>

## **FACTOR ZOO**


[FACTOR  ZOO](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo)
: TOTAL 1049 FACTORS NOW 

[量价因子](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/runs.md)

- [振幅](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/runs_amplitude.md)
- [标准差](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/runs_std.md)
- [高阶矩](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/runs_higher_moment.md)
- [成交占比](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/runs_turnover.md)
- [流动性](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/runs_liquidity.md)
- [量价相关系数](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/runs_corr.md)
- [极值信息](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/runs_idx.md)
- [券商因子复现](https://github.com/chaosquant2022/ML-Quant/tree/main/factor_zoo/券商因子IC.md)

<BR>

## 公众号文章 ##

### QUANTML-QLIB 相关 ### 

- [<font color=#871F78>QuantML-Qlib 教程</font>](https://mp.weixin.qq.com/s/3RM5nH7WXs-X8LFEcZwCwg)

- [QuantML-Qlib Factor | DeepSeek自动因子挖掘及优化方案](https://mp.weixin.qq.com/s/GuNe_sf8S6qesgBn00Vz8g)

- [QuantML-Qlib Model | 复现DeepSeek核心结构用于选股](https://mp.weixin.qq.com/s/eUKoT2VoAUpUJUk8QdIw0w)

- [QuantML-Qlib Factor | 融合TA-Lib100+技术指标，自定义构建AlphaZoo](https://mp.weixin.qq.com/s/-GhQltRShyGJqLZ2wJaTfA)

- [QuantML-Qlib LLM | GPT-4o复现因子计算代码](http://mp.weixin.qq.com/s?__biz=Mzg2MzAwNzM0NQ==&mid=2247484355&idx=1&sn=0e2e068277314d93d0373ad5e1b0da82&chksm=ce7e64ddf909edcb0f2894f353b26825800a7862dfb6a53b692b212ae5e93e43c0d7b1ee71cf#rd) 

- [QuantML-QlibDB | Clickhouse 行情存储与读取方案](http://mp.weixin.qq.com/s?__biz=Mzg2MzAwNzM0NQ==&mid=2247484391&idx=1&sn=b56d54740da5d77bef608d787033e321&chksm=ce7e64f9f909edef46da039efbeaf07b636ef08477a3f4ba2b49dea329d2c29b71635a809aca#rd) 

- [QuantML-Qlib开发版 | AAAI最佳论文Informer用于金融市场预测【附代码】](http://mp.weixin.qq.com/s?__biz=Mzg2MzAwNzM0NQ==&mid=2247484065&idx=1&sn=d666c3cd759ceffbdb304c1097a4ebb8&chksm=ce7e65bff909eca9a4fedaef3b9edabf3d4d65c11f38d6edc80e973a9cc6d4c9944944666071#rd) 

- [QuantML-Qlib开发版 | MoE混合专家系统用于提升Transformer表现【附代码】](http://mp.weixin.qq.com/s?__biz=Mzg2MzAwNzM0NQ==&mid=2247484124&idx=1&sn=735f6f9488e202679ad96b3d19329673&chksm=ce7e65c2f909ecd438e908babf20726acc73162f9a5198c445f5bf3b1bc8ed6ed16474cbecfd#rd)

### paper 相关 ### 

- [券商研报因子复现及表现研究](http://mp.weixin.qq.com/s?__biz=Mzg2MzAwNzM0NQ==&mid=2247484329&idx=1&sn=24f18ad20fc0a44ba09a19d43becf651&chksm=ce7e64b7f909eda171118d001451a569509a67bb2d486f5affdaa2824dab5b824ee4bd7b3052#rd) 

- [Kaggle - Optiver trading at the close第一名解决方案及部分代码
](https://mp.weixin.qq.com/s/5sLVB6GwcdQXvkE2T82KCg)

- [TradingAgents：基于多智能体LLM的金融交易框架](https://mp.weixin.qq.com/s/7mDnrEOucf6i8yEGkyIc2w)

- [DeepScalper：深度强化学习捕捉日内交易的短暂机会](https://mp.weixin.qq.com/s/SnMejEiC4Ebt8_k8G4iJoA)

- [AAAI-2024 | MASTER 结合市场信息的自动特征选择的股票预测模型，25%年化收益，附代码](http://mp.weixin.qq.com/s?__biz=Mzg2MzAwNzM0NQ==&mid=2247483818&idx=1&sn=8f17951f57c801a612c7d47f3e1c3a77&chksm=ce7e66b4f909efa2a462cb0640427342a98fe733beeb3e275b1625b9e6f72dcd29a5adb196f6#rd) 

- [AAAI-23 | PEN: 可解释的结合新闻及社交媒体文本数据的股票预测神经网络模型](http://mp.weixin.qq.com/s?__biz=Mzg2MzAwNzM0NQ==&mid=2247483925&idx=1&sn=711b4a193f231442ead1a7709fc9b29a&chksm=ce7e650bf909ec1dc65070e866ee1d6c0127291efb093bb982ae5652aa8232155b2a757ca5d7#rd) 

- [AAAI-24 | EarnHFT:针对高频交易的分层强化学习（RL）框架](http://mp.weixin.qq.com/s?__biz=Mzg2MzAwNzM0NQ==&mid=2247483884&idx=1&sn=b6cde76f0cecd07f19179fce94b67922&chksm=ce7e66f2f909efe4a8e9dcae71358111132135ba8f36bbe40faa5e0a2f42c2291f6ebbe9e4c6#rd) 

<BR>

MORE:  [公众号QuantML](https://github.com/chaosquant2022/ML-Quant/tree/main/papers/公众号文章.md)

## 知识星球 ## 

[模型，因子相关论文及代码发布地址](https://t.zsxq.com/179npRquk)

<BR>


## **QUANT-RESOURCES**:

- [Awesome-quant](https://github.com/wilsonfreitas/awesome-quant)

- [Awesome-quant(Chinese)](https://github.com/thuquant/awesome-quant)

- [Awesome-Quant-Machine-Learning-Trading](https://github.com/grananqvist/Awesome-Quant-Machine-Learning-Trading)

- [量化交易全攻略：从入门到精通的终极指南](https://mp.weixin.qq.com/s/Pb4OwqJevY1e2qA7aSIJ2w)

<BR>



## **PAPERS AND MODELS**:

- Time-Series Works and Conferences [Time-Series-Works-Conferences
](https://github.com/lixus7/Time-Series-Works-Conferences)

- Time Series Library [TSlib](https://github.com/thuml/Time-Series-Library/tree/main)

- DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation [DDG-DA](https://arxiv.org/abs/2201.04038)

- Awesome Time Series Forecasting/Prediction Papers [TSFpaper](https://github.com/ddz16/TSFpaper/tree/a4e106b9579d49ba55370e70935e9acff467120a) 

- Temporal 2D-Variation Modeling for General Time Series Analysis [TimesNet](extension://oikmahiipjniocckomdccmplodldodja/pdf-viewer/web/viewer.html?file=https%3A%2F%2Fopenreview.net%2Fpdf%3Fid%3Dju_Uqw384Oq)

- A Survey on Time-Series Pre-Trained Models [time-series-ptms](https://github.com/qianlima-lab/time-series-ptms)

- Pytorch Transformer based Time Series Models [transformer-ts](https://github.com/kashif/pytorch-transformer-ts)

- Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning [alphagen](https://github.com/RL-MLDM/alphagen)

- Awesome-GNN4TS [awesome-gnn4ts](https://github.com/KimMeen/Awesome-GNN4TS)

- MASTER: Market-Guided Stock Transformer for Stock Price Forecasting [MASTER](https://github.com/SJTU-Quant/MASTER)

<BR>




<br>
UPDATING...<br>
<br>
欢迎交流

<br>
<div align="left">
	<img src="ML-Quant.jpg" width="50%" >
	<img src="GZH.jpg" width="27.5%" >
 	<!-- <img src="wechat.jpg" width="20.83%"> -->
	<!-- <img src="ML-Quant.jpg" width="25%"> -->
</div>