[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-cbailes--awesome-deep-trading":3,"tool-cbailes--awesome-deep-trading":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",160784,2,"2026-04-19T11:32:54",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",109154,"2026-04-18T11:18:24",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":78,"owner_twitter":75,"owner_website":79,"owner_url":80,"languages":75,"stars":81,"forks":82,"last_commit_at":83,"license":84,"difficulty_score":85,"env_os":86,"env_gpu":87,"env_ram":87,"env_deps":88,"category_tags":91,"github_topics":92,"view_count":32,"oss_zip_url":75,"oss_zip_packed_at":75,"status":17,"created_at":106,"updated_at":107,"faqs":108,"releases":109},9683,"cbailes\u002Fawesome-deep-trading","awesome-deep-trading","List of awesome resources for machine learning-based algorithmic trading","awesome-deep-trading 是一个专为人工智能量化交易打造的开源资源宝库，系统性地汇集了将深度学习、神经网络及机器学习应用于算法交易的高质量代码、学术论文与实用指南。面对金融市场中模型构建难、前沿技术分散且复现成本高的问题，它通过精心整理的分类目录，帮助用户快速定位从卷积神经网络（CNN）、长短期记忆网络（LSTM）到生成对抗网络（GAN）和强化学习等关键技术在交易策略、高频交易、投资组合管理及加密货币分析中的具体应用案例。\n\n该项目特别适合量化研究员、AI 开发者以及金融科技领域的学生使用。无论是希望复现经典论文实验的研究者，还是寻求构建智能交易机器人灵感的工程师，都能在此找到经过筛选的权威资料，包括大量关于市场预测、订单簿分析及情绪感知的核心论文链接，以及配套的数据集和模拟环境资源。其独特亮点在于不仅涵盖了传统股票市场的深度对冲与策略优化，还深入探讨了社交数据处理与行为分析等新兴交叉领域，并坚持完全开放获取原则，允许用户在 MIT 或 CC-BY 协议下自由使用与二次开发，是进入 AI 量化交易领域不可多得的入门与进阶指南。","# awesome-deep-trading\n[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome)\n\nList of code, papers, and resources for AI\u002Fdeep learning\u002Fmachine learning\u002Fneural networks applied to algorithmic trading.\n\nOpen access: all rights granted for use and re-use of any kind, by anyone, at no cost, under your choice of either the free MIT License or Creative Commons CC-BY International Public License.\n\n© 2021 Craig Bailes ([@cbailes](https:\u002F\u002Fgithub.com\u002Fcbailes) | [Patreon](https:\u002F\u002Fwww.patreon.com\u002Fcraigbailes) | [contact@craigbailes.com](mailto:contact@craigbailes.com))\n\n# Contents\n- [Papers](#papers)\n  * [Meta Analyses & Systematic Reviews](#meta-analyses--systematic-reviews)\n  * [Convolutional Neural Networks (CNNs)](#convolutional-neural-networks-cnns)\n  * [Long Short-Term Memory (LSTMs)](#long-short-term-memory-lstms)\n  * [Generative Adversarial Networks (GANs)](#generative-adversarial-networks-gans)\n  * [High Frequency](#high-frequency)\n  * [Portfolio](#portfolio)\n  * [Reinforcement Learning](#reinforcement-learning)\n  * [Vulnerabilities](#vulnerabilities)\n  * [Cryptocurrency](#cryptocurrency)\n  * [Social Processing](#social-processing)\n    + [Behavioral Analysis](#behavioral-analysis)\n    + [Sentiment Analysis](#sentiment-analysis)\n- [Repositories](#repositories)\n  * [Generative Adversarial Networks (GANs)](#generative-adversarial-networks-gans-1)\n  * [Guides](#guides)\n  * [Cryptocurrency](#cryptocurrency-1) \n  * [Datasets](#datasets)\n    + [Simulation](#simulation)\n- [Resources](#resources)\n  * [Presentations](#presentations)\n  * [Courses](#courses)\n  * [Further Reading](#further-reading)\n\n# Papers\n\n* [Classification-based Financial Markets Prediction using Deep Neural Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.08604) - Matthew Dixon, Diego Klabjan, Jin Hoon Bang (2016)\n* [Deep Learning for Limit Order Books](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1601.01987) - Justin Sirignano (2016)\n* [High-Frequency Trading Strategy Based on Deep Neural Networks](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007%2F978-3-319-42297-8_40) - Andrés Arévalo, Jaime Niño, German Hernández, Javier Sandoval (2016)\n* [A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.10059) - Zhengyao Jiang, Dixing Xu, Jinjun Liang (2017)\n* [Agent Inspired Trading Using Recurrent Reinforcement Learning and LSTM Neural Networks](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.07338.pdf) - David W. Lu (2017)\n* [Deep Hedging](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.03042) - Hans Bühler, Lukas Gonon, Josef Teichmann, Ben Wood (2018)\n* [Stock Trading Bot Using Deep Reinforcement Learning](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-981-10-8201-6_5) - Akhil Raj Azhikodan, Anvitha G. K. Bhat, Mamatha V. Jadhav (2018)\n* [Financial Trading as a Game: A Deep Reinforcement Learning Approach](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1807.02787) - Chien Yi Huang (2018)\n* [Practical Deep Reinforcement Learning Approach for Stock Trading](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1811.07522) - Zhuoran Xiong, Xiao-Yang Liu, Shan Zhong, Hongyang Yang, Anwar Walid (2018)\n* [Algorithmic Trading and Machine Learning Based on GPU](http:\u002F\u002Fceur-ws.org\u002FVol-2147\u002Fp09.pdf) - Mantas Vaitonis, Saulius Masteika, Konstantinas Korovkinas (2018)\n* [A quantitative trading method using deep convolution neural network ](https:\u002F\u002Fiopscience.iop.org\u002Farticle\u002F10.1088\u002F1757-899X\u002F490\u002F4\u002F042018\u002Fpdf) - HaiBo Chen, DaoLei Liang, LL Zhao (2019)\n* [Deep learning in exchange markets](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0167624518300702) - Rui Gonçalves, Vitor Miguel Ribeiro, Fernando Lobo Pereira, Ana Paula Rocha (2019)\n* [Financial Trading Model with Stock Bar Chart Image Time Series with Deep Convolutional Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.04610) - Omer Berat Sezer, Ahmet Murat Ozbayoglu (2019)\n* [Deep Reinforcement Learning for Financial Trading Using Price Trailing](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8683161) -  Konstantinos Saitas Zarkias, Nikolaos Passalis, Avraam Tsantekidis, Anastasios Tefas (2019)\n* [Cooperative Multi-Agent Reinforcement Learning Framework for Scalping Trading](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.00441) - Uk Jo, Taehyun Jo, Wanjun Kim, Iljoo Yoon, Dongseok Lee, Seungho Lee (2019)\n* [Improving financial trading decisions using deep Q-learning: Predicting the number of shares, action strategies, and transfer learning](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417418306134) - Gyeeun Jeong, Ha Young Kim (2019)\n* [Deep Execution - Value and Policy Based Reinforcement Learning for Trading and Beating Market Benchmarks](https:\u002F\u002Fpapers.ssrn.com\u002Fsol3\u002Fpapers.cfm?abstract_id=3374766) - Kevin Dabérius, Elvin Granat, Patrik Karlsson (2019)\n* [An Empirical Study of Machine Learning Algorithms for Stock Daily Trading Strategy](https:\u002F\u002Fwww.hindawi.com\u002Fjournals\u002Fmpe\u002F2019\u002F7816154\u002Fref\u002F) - Dongdong Lv, Shuhan Yuan, Meizi Li, Yang Xiang (2019)\n* [Recipe for Quantitative Trading with Machine Learning](http:\u002F\u002Fdx.doi.org\u002F10.2139\u002Fssrn.3232143) - Daniel Alexandre Bloch (2019)\n* [Exploring Possible Improvements to Momentum Strategies with Deep Learning](http:\u002F\u002Fhdl.handle.net\u002F2105\u002F49940) - Adam Takács, X. Xiao (2019)\n* [Enhancing Time Series Momentum Strategies Using Deep Neural Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.04912) - Bryan Lim, Stefan Zohren, Stephen Roberts (2019)\n* [Multi-Agent Deep Reinforcement Learning for Liquidation Strategy Analysis](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.11046) - Wenhang Bao, Xiao-yang Liu (2019)\n* [Deep learning-based feature engineering for stock price movement prediction](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0950705118305264) - Wen Long, Zhichen Lu, Lingxiao Cui (2019)\n* [Review on Stock Market Forecasting & Analysis](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340583328_Review_on_Stock_Market_Forecasting_Analysis-LSTM_Long-Short_Term_Memory_Holt's_Seasonal_MethodANN_Artificial_Neural_Network_ARIMA_Auto_Regressive_Integrated_Minimum_Average_PCA_MLP_Multi_Layers_Percep) - Anirban Bal, Debayan Ganguly, Kingshuk Chatterjee (2019)\n* [Neural Networks as a Forecasting Tool in the Context of the Russian Financial Market Digitalization](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340474330_Neural_Networks_as_a_Forecasting_Tool_in_the_Context_of_the_Russian_Financial_Market_Digitalization) - Valery Aleshin, Oleg Sviridov, Inna Nekrasova, Dmitry Shevchenko (2020)\n* [Deep Hierarchical Strategy Model for Multi-Source Driven Quantitative Investment](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8743385) - Chunming Tang, Wenyan Zhu, Xiang Yu (2019)\n* [Finding Efficient Stocks in BSE100: Implementation of Buffet Approach INTRODUCTION](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340501895_Asian_Journal_of_Management_Finding_Efficient_Stocks_in_BSE100_Implementation_of_Buffet_Approach_INTRODUCTION) - Sherin Varghese, Sandeep Thakur, Medha Dhingra (2020)\n* [Deep Learning in Asset Pricing](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.00745) - Luyang Chen, Markus Pelger, Jason Zhu (2020)\n\n## Meta Analyses & Systematic Reviews\n* [Application of machine learning in stock trading: a review](http:\u002F\u002Fdx.doi.org\u002F10.14419\u002Fijet.v7i2.33.15479) - Kok Sheng Tan, Rajasvaran Logeswaran (2018)\n* [Evaluating the Performance of Machine Learning Algorithms in Financial Market Forecasting: A Comprehensive Survey](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.07786) - Lukas Ryll, Sebastian Seidens (2019)\n* [Reinforcement Learning in Financial Markets](https:\u002F\u002Fwww.mdpi.com\u002F2306-5729\u002F4\u002F3\u002F110\u002Fpdf) - Terry Lingze Meng, Matloob Khushi (2019)\n* [Financial Time Series Forecasting with Deep Learning: A Systematic Literature Review: 2005-2019](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.13288) - Omer Berat Sezer, Mehmet Ugur Gudelek, Ahmet Murat Ozbayoglu (2019)\n* [A systematic review of fundamental and technical analysis of stock market predictions](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F335274959_A_systematic_review_of_fundamental_and_technical_analysis_of_stock_market_predictions) - Isaac kofi Nti, Adebayo Adekoya, Benjamin Asubam Weyori (2019)\n\n## Convolutional Neural Networks (CNNs)\n* [A deep learning based stock trading model with 2-D CNN trend detection](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F323131323_A_deep_learning_based_stock_trading_model_with_2-D_CNN_trend_detection) - Ugur Gudelek, S. Arda Boluk, Murat Ozbayoglu, Murat Ozbayoglu (2017)\n* [Algorithmic Financial Trading with Deep Convolutional Neural Networks: Time Series to Image Conversion Approach](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F324802031_Algorithmic_Financial_Trading_with_Deep_Convolutional_Neural_Networks_Time_Series_to_Image_Conversion_Approach) - Omer Berat Sezar, Murat Ozbayoglu (2018)\n* [DeepLOB: Deep Convolutional Neural Networks for Limit Order Books](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8673598) - Zihao Zhang, Stefan Zohren, Stephen Roberts (2019)\n\n## Long Short-Term Memory (LSTMs)\n* [Application of Deep Learning to Algorithmic Trading, Stanford CS229](http:\u002F\u002Fcs229.stanford.edu\u002Fproj2017\u002Ffinal-reports\u002F5241098.pdf) - Guanting Chen, Yatong Chen, Takahiro Fushimi (2017)\n* [Stock Prices Prediction using Deep Learning Models](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.12227) - Jialin Liu, Fei Chao, Yu-Chen Lin, Chih-Min Lin (2019)\n* [Deep Learning for Stock Market Trading: A Superior Trading Strategy?](https:\u002F\u002Fdoi.org\u002F10.14311\u002FNNW.2019.29.011) - D. Fister, J. C. Mun, V. Jagrič, T. Jagrič, (2019)\n* [Performance Evaluation of Recurrent Neural Networks for Short-Term Investment Decision in Stock Market](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F339751012_Performance_Evaluation_of_Recurrent_Neural_Networks_for_Short-Term_Investment_Decision_in_Stock_Market) - Alexandre P. da Silva, Silas S. L. Pereira, Mário W. L. Moreira, Joel J. P. C. Rodrigues, Ricardo A. L. Rabêlo, Kashif Saleem (2020)\n* [Research on financial assets transaction prediction model based on LSTM neural network](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs00521-020-04992-7) - Xue Yan, Wang Weihan & Miao Chang (2020)\n* [Prediction Of Stock Trend For Swing Trades Using Long Short-Term Memory Neural Network Model](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340789607_Prediction_Of_Stock_Trend_For_Swing_Trades_Using_Long_Short-Term_Memory_Neural_Network_Model) - Varun Totakura, V. Devasekhar, Madhu Sake (2020)\n* [A novel Deep Learning Framework: Prediction and Analysis of Financial Time Series using CEEMD and LSTM](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0957417420304334) - Yong'an Zhang, Binbin Yan, Memon Aasma (2020)\n* [Deep Stock Predictions](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.04992) - Akash Doshi, Alexander Issa, Puneet Sachdeva, Sina Rafati, Somnath Rakshit (2020)\n\n## Generative Adversarial Networks (GANs)\n* [Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination](https:\u002F\u002Fdeepai.org\u002Fpublication\u002Fgenerative-adversarial-networks-for-financial-trading-strategies-fine-tuning-and-combination) - Adriano Koshiyama (2019)\n* [Stock Market Prediction Based on Generative Adversarial Network](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.procs.2019.01.256) - Kang Zhang, Guoqiang Zhong, Junyu Dong, Shengke Wang, Yong Wang (2019)\n* [Generative Adversarial Network for Stock Market price Prediction](https:\u002F\u002Fcs230.stanford.edu\u002Fprojects_fall_2019\u002Freports\u002F26259829.pdf) - Ricardo Alberto Carrillo Romero (2019)\n* [Generative Adversarial Network for Market Hourly Discrimination](https:\u002F\u002Fmpra.ub.uni-muenchen.de\u002Fid\u002Feprint\u002F99846) - Luca Grilli, Domenico Santoro (2020)\n\n## High Frequency\n* [Algorithmic Trading Using Deep Neural Networks on High Frequency Data](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-66963-2_14) - Andrés Arévalo, Jaime Niño, German Hernandez, Javier Sandoval, Diego León, Arbey Aragón (2017)\n* [Stock Market Prediction on High-Frequency Data Using Generative Adversarial Nets](https:\u002F\u002Fdoi.org\u002F10.1155\u002F2018\u002F4907423) - Xingyu Zhou, Zhisong Pan, Guyu Hu, Siqi Tang, Cheng Zhao (2018)\n* [Deep Neural Networks in High Frequency Trading](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.01506) - Prakhar Ganesh, Puneet Rakheja (2018)\n* [Application of Machine Learning in High Frequency Trading of Stocks](https:\u002F\u002Fwww.ijser.org\u002Fresearchpaper\u002FApplication-of-Machine-Learning-in-High-Frequency-Trading-of-Stocks.pdf) - Obi Bertrand Obi (2019)\n\n## Portfolio\n* [Multi Scenario Financial Planning via Deep Reinforcement Learning AI](https:\u002F\u002Fpapers.ssrn.com\u002Fsol3\u002Fpapers.cfm?abstract_id=3516480) - Gordon Irlam (2020)\n* [G-Learner and GIRL: Goal Based Wealth Management with Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.10990) - Matthew Dixon, Igor Halperin (2020)\n* [Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States](https:\u002F\u002Fwww.aaai.org\u002FPapers\u002FAAAI\u002F2020GB\u002FAAAI-YeY.4483.pdf) - Yunan Ye, Hengzhi Pei, Boxin Wang, Pin-Yu Chen, Yada Zhu, Jun Xiao, Bo Li (2020)\n\n## Reinforcement Learning\n* [Reinforcement learning in financial markets - a survey](http:\u002F\u002Fhdl.handle.net\u002F10419\u002F183139) - Thomas G. Fischer (2018)\n* [AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.02646) - Jingyuan Wang, Yang Zhang, Ke Tang, Junjie Wu, Zhang Xiong\n* [Capturing Financial markets to apply Deep Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.04373) - Souradeep Chakraborty (2019)\n* [Reinforcement Learning for FX trading](http:\u002F\u002Fstanford.edu\u002Fclass\u002Fmsande448\u002F2019\u002FFinal_reports\u002Fgr2.pdf) - Yuqin Dai, Chris Wang, Iris Wang, Yilun Xu (2019)\n* [An Application of Deep Reinforcement Learning to Algorithmic Trading](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.06627) - Thibaut Théate, Damien Ernst (2020)\n* [Single asset trading: a recurrent reinforcement learning approach](http:\u002F\u002Furn.kb.se\u002Fresolve?urn=urn:nbn:se:mdh:diva-47505) - Marko Nikolic (2020)\n* [Beat China’s stock market by using Deep reinforcement learning](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FHuang_Gang9\u002Fpublication\u002F340438304_Beat_China's_stock_market_by_using_Deep_reinforcement_learning\u002Flinks\u002F5e88e007299bf130797c7a68\u002FBeat-Chinas-stock-market-by-using-Deep-reinforcement-learning.pdf) - Gang Huang, Xiaohua Zhou, Qingyang Song (2020)\n* [An Adaptive Financial Trading System Using Deep Reinforcement Learning With Candlestick Decomposing Features](https:\u002F\u002Fdoi.org\u002F10.1109\u002FACCESS.2020.2982662) - Ding Fengqian, Luo Chao (2020)\n* [Application of Deep Q-Network in Portfolio Management](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.06365) - Ziming Gao, Yuan Gao, Yi Hu, Zhengyong Jiang, Jionglong Su (2020)\n* [Deep Reinforcement Learning Pairs Trading with a Double Deep Q-Network](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9031159) - Andrew Brim (2020)\n* [A reinforcement learning model based on reward correction for quantitative stock selection](https:\u002F\u002Fdoi.org\u002F10.1088\u002F1757-899X\u002F768\u002F7\u002F072036) - Haibo Chen, Chenyu Zhang, Yunke Li (2020)\n* [AAMDRL: Augmented Asset Management with Deep Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08497) - Eric Benhamou, David Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay, Jamal Atif (2020)\n\n## Guides\n* [Stock Price Prediction And Forecasting Using Stacked LSTM- Deep Learning](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=H6du_pfuznE) - Krish Naik (2020) \n* [Comparing Arima Model and LSTM RNN Model in Time-Series Forecasting](https:\u002F\u002Fanalyticsindiamag.com\u002Fcomparing-arima-model-and-lstm-rnn-model-in-time-series-forecasting\u002F) - Vaibhav Kumar (2020)\n* [LSTM to predict Dow Jones Industrial Average: A Time Series forecasting model](https:\u002F\u002Fmedium.com\u002Fanalytics-vidhya\u002Flstm-to-predict-dow-jones-industrial-average-time-series-647b0115f28c) - Sarit Maitra (2020)\n\n## Vulnerabilities\n* [Adversarial Attacks on Deep Algorithmic Trading Policies](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.11388) - Yaser Faghan, Nancirose Piazza, Vahid Behzadan, Ali Fathi (2020)\n\n## Cryptocurrency\n* [Recommending Cryptocurrency Trading Points with Deep Reinforcement Learning Approach](https:\u002F\u002Fdoi.org\u002F10.3390\u002Fapp10041506) - Otabek Sattarov, Azamjon Muminov, Cheol Won Lee, Hyun Kyu Kang, Ryumduck Oh, Junho Ahn, Hyung Jun Oh, Heung Seok Jeon (2020)\n\n## Social Processing\n### Behavioral Analysis\n* [Can Deep Learning Predict Risky Retail Investors? A Case Study in Financial Risk Behavior Forecasting](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F329734839_Can_Deep_Learning_Predict_Risky_Retail_Investors_A_Case_Study_in_Financial_Risk_Behavior_Forecasting) - Yaodong Yang, Alisa Kolesnikova, Stefan Lessmann, Tiejun Ma, Ming-Chien Sung, Johnnie E.V. Johnson (2019)\n* [Investor behaviour monitoring based on deep learning](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F0144929X.2020.1717627?casa_token=heptguQeb3kAAAAA%3AB1D3L4udpW0l3nw0sJHSpZ9tvDjptW3HfDqa_3XrUS-9owFARbHnurpSdtCy54KzR05aTdNTwhbnMA) - Song Wang, Xiaoguang Wang, Fanglin Meng, Rongjun Yang, Yuanjun Zhao (2020)\n\n### Sentiment Analysis\n* [Improving Decision Analytics with Deep Learning: The Case of Financial Disclosures](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1508.01993) - Stefan Feuerriegel, Ralph Fehrer (2015)\n* [Big Data: Deep Learning for financial sentiment analysis](https:\u002F\u002Fjournalofbigdata.springeropen.com\u002Farticles\u002F10.1186\u002Fs40537-017-0111-6) - Sahar Sohangir, Dingding Wang, Anna Pomeranets, Taghi M. Khoshgoftaar (2018)\n* [Using Machine Learning to Predict Stock Prices](https:\u002F\u002Fmedium.com\u002Fanalytics-vidhya\u002Fusing-machine-learning-to-predict-stock-prices-c4d0b23b029a) - Vivek Palaniappan (2018)\n* [Stock Prediction Using Twitter](https:\u002F\u002Ftowardsdatascience.com\u002Fstock-prediction-using-twitter-e432b35e14bd) - Khan Saad Bin Hasan (2019)\n* [Sentiment and Knowledge Based Algorithmic Trading with Deep Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.09403) - Abhishek Nan, Anandh Perumal, Osmar R. Zaiane (2020)\n\n# Repositories\n* [Yvictor\u002FTradingGym](https:\u002F\u002Fgithub.com\u002FYvictor\u002FTradingGym) - Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo\n* [Rachnog\u002FDeep-Trading](https:\u002F\u002Fgithub.com\u002FRachnog\u002FDeep-Trading) - Experimental time series forecasting\n* [jobvisser03\u002Fdeep-trading-advisor](https:\u002F\u002Fgithub.com\u002Fjobvisser03\u002Fdeep-trading-advisor) - Deep Trading Advisor uses MLP, CNN, and RNN+LSTM with Keras, zipline, Dash and Plotly\n* [rosdyana\u002FCNN-Financial-Data](https:\u002F\u002Fgithub.com\u002Frosdyana\u002FCNN-Financial-Data) - Deep Trading using a Convolutional Neural Network\n* [iamSTone\u002FDeep-trader-CNN-kospi200futures](https:\u002F\u002Fgithub.com\u002FiamSTone\u002FDeep-trader-CNN-kospi200futures) - Kospi200 index futures Prediction using CNN\n* [ha2emnomer\u002FDeep-Trading](https:\u002F\u002Fgithub.com\u002Fha2emnomer\u002FDeep-Trading) - Keras-based LSTM RNN \n* [gujiuxiang\u002FDeep_Trader.pytorch](https:\u002F\u002Fgithub.com\u002Fgujiuxiang\u002FDeep_Trader.pytorch) - This project uses Reinforcement learning on stock market and agent tries to learn trading. PyTorch based.\n* [ZhengyaoJiang\u002FPGPortfolio](https:\u002F\u002Fgithub.com\u002FZhengyaoJiang\u002FPGPortfolio) - PGPortfolio: Policy Gradient Portfolio, the source code of \"A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem\"\n* [yuriak\u002FRLQuant](https:\u002F\u002Fgithub.com\u002Fyuriak\u002FRLQuant) - Applying Reinforcement Learning in Quantitative Trading (Policy Gradient, Direct RL)\n* [ucaiado\u002FQLearning_Trading](https:\u002F\u002Fgithub.com\u002Fucaiado\u002FQLearning_Trading) - Trading Using Q-Learning\n* [laikasinjason\u002Fdeep-q-learning-trading-system-on-hk-stocks-market](https:\u002F\u002Fgithub.com\u002Flaikasinjason\u002Fdeep-q-learning-trading-system-on-hk-stocks-market) - Deep Q learning implementation on the Hong Kong Stock Exchange\n* [golsun\u002Fdeep-RL-trading](https:\u002F\u002Fgithub.com\u002Fgolsun\u002Fdeep-RL-trading) - Codebase for paper \"Deep reinforcement learning for time series: playing idealized trading games\" by Xiang Gao\n* [huseinzol05\u002FStock-Prediction-Models](https:\u002F\u002Fgithub.com\u002Fhuseinzol05\u002FStock-Prediction-Models) - Gathers machine learning and deep learning models for Stock forecasting, included trading bots and simulations\n* [jiewwantan\u002FStarTrader](https:\u002F\u002Fgithub.com\u002Fjiewwantan\u002FStarTrader) - Trains an agent to trade like a human using a deep reinforcement learning algorithm: deep deterministic policy gradient (DDPG) learning algorithm\n* [notadamking\u002FRLTrader](https:\u002F\u002Fgithub.com\u002Fnotadamking\u002FRLTrader) - A cryptocurrency trading environment using deep reinforcement learning and OpenAI's gym\n\n## Generative Adversarial Networks (GANs)\n* [borisbanushev\u002Fstockpredictionai](https:\u002F\u002Fgithub.com\u002Fborisbanushev\u002Fstockpredictionai) - A notebook for stock price movement prediction using an LSTM generator and CNN discriminator\n* [kah-ve\u002FMarketGAN](https:\u002F\u002Fgithub.com\u002Fkah-ve\u002FMarketGAN) - Implementing a Generative Adversarial Network on the Stock Market\n\n## Cryptocurrency\n* [samre12\u002Fdeep-trading-agent](https:\u002F\u002Fgithub.com\u002Fsamre12\u002Fdeep-trading-agent) - Deep Reinforcement Learning-based trading agent for Bitcoin using DeepSense Network for Q function approximation.\n* [ThirstyScholar\u002Ftrading-bitcoin-with-reinforcement-learning](https:\u002F\u002Fgithub.com\u002FThirstyScholar\u002Ftrading-bitcoin-with-reinforcement-learning) - Trading Bitcoin with Reinforcement Learning\n* [lefnire\u002Ftforce_btc_trader](https:\u002F\u002Fgithub.com\u002Flefnire\u002Ftforce_btc_trader) - A TensorForce-based Bitcoin trading bot (algo-trader). Uses deep reinforcement learning to automatically buy\u002Fsell\u002Fhold BTC based on price history.\n\n## Datasets\n* [kaggle\u002FHuge Stock Market Dataset](https:\u002F\u002Fwww.kaggle.com\u002Fborismarjanovic\u002Fprice-volume-data-for-all-us-stocks-etfs) - Historical daily prices and volumes of all U.S. stocks and ETFs\n* [Alpha Vantage](https:\u002F\u002Fwww.alphavantage.co\u002F) - Free APIs in JSON and CSV formats, realtime and historical stock data, FX and cryptocurrency feeds, 50+ technical indicators  \n* [Quandl](https:\u002F\u002Fquandl.com\u002F)\n\n### Simulation\n* [Generating Realistic Stock Market Order Streams](https:\u002F\u002Fopenreview.net\u002Fpdf?id=rke41hC5Km) - Anonymous Authors (2018)\n* [Deep Hedging: Learning to Simulate Equity Option Markets](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.01700) - Magnus Wiese, Lianjun Bai, Ben Wood, Hans Buehler (2019)\n\n# Resources\n## Presentations\n* [BigDataFinance Neural Networks Intro](http:\u002F\u002Fbigdatafinance.eu\u002Fwp\u002Fwp-content\u002Fuploads\u002F2016\u002F06\u002FTefas_BigDataFinanceNeuralNetworks_Intro_Web.pdf) - Anastasios Tefas, Assistant Professor at Aristotle University of Thessaloniki (2016)\n* [Trading Using Deep Learning: Motivation, Challenges, Solutions](http:\u002F\u002Fon-demand.gputechconf.com\u002Fgtc-il\u002F2017\u002Fpresentation\u002Fsil7121-yam-peleg-deep-learning-for-high-frequency-trading%20(2).pdf) - Yam Peleg, GPU Technology Conference (2017)\n* [FinTech, AI, Machine Learning in Finance](https:\u002F\u002Fwww.slideshare.net\u002Fsanjivdas\u002Ffintech-ai-machine-learning-in-finance) - Sanjiv Das (2018)\n* [Deep Residual Learning for Portfolio Optimization:With Attention and Switching Modules](https:\u002F\u002Fengineering.nyu.edu\u002Fsites\u002Fdefault\u002Ffiles\u002F2019-03\u002FNYU%20FRE%20Seminar-Jifei%20Wang%20%28slides%29.pdf) - Jeff Wang, Ph.D., NYU\n\n## Courses\n* [Artificial Intelligence for Trading (ND880) nanodegree at Udacity](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Fai-for-trading--nd880) (+[GitHub code repo](https:\u002F\u002Fgithub.com\u002Fudacity\u002Fartificial-intelligence-for-trading))\n* [Neural Networks in Trading course by Dr. Ernest P. Chan at Quantra](https:\u002F\u002Fquantra.quantinsti.com\u002Fcourse\u002Fneural-networks-deep-learning-trading-ernest-chan)\n* [Machine Learning and Reinforcement Learning in Finance Specialization by NYU at Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fmachine-learning-reinforcement-finance)\n\n## Meetups\n* [Artificial Intelligence in Finance & Algorithmic Trading on Meetup](https:\u002F\u002Fwww.meetup.com\u002FArtificial-Intelligence-in-Finance-Algorithmic-Trading\u002F) (New York City)\n\n## Further Reading\n* [Neural networks for algorithmic trading. Simple time series forecasting](https:\u002F\u002Fmedium.com\u002F@alexrachnog\u002Fneural-networks-for-algorithmic-trading-part-one-simple-time-series-forecasting-f992daa1045a) - Alex Rachnog (2016)\n* [Predicting Cryptocurrency Prices With Deep Learning](https:\u002F\u002Fdashee87.github.io\u002Fdeep%20learning\u002Fpython\u002Fpredicting-cryptocurrency-prices-with-deep-learning\u002F) - David Sheehan (2017)\n* [Introduction to Learning to Trade with Reinforcement Learning](http:\u002F\u002Fwww.wildml.com\u002F2018\u002F02\u002Fintroduction-to-learning-to-trade-with-reinforcement-learning\u002F) - Denny Britz (2018)\n* [Webinar: How to Forecast Stock Prices Using Deep Neural Networks](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RMh8AUTQWQ8) - Erez Katz, Lucena Research (2018)\n* [Creating Bitcoin trading bots that don’t lose money](https:\u002F\u002Ftowardsdatascience.com\u002Fcreating-bitcoin-trading-bots-that-dont-lose-money-2e7165fb0b29) - Adam King (2019)\n* [Why Deep Reinforcement Learning Can Help Improve Trading Efficiency](https:\u002F\u002Fmedium.com\u002F@viktortachev\u002Fwhy-deep-reinforcement-learning-can-help-improve-trading-efficiency-5af57e8faf9d) - Viktor Tachev (2019)\n* [Optimizing deep learning trading bots using state-of-the-art techniques](https:\u002F\u002Ftowardsdatascience.com\u002Fusing-reinforcement-learning-to-trade-bitcoin-for-massive-profit-b69d0e8f583b) - Adam King (2019)\n* [Using the latest advancements in deep learning to predict stock price movements](https:\u002F\u002Ftowardsdatascience.com\u002Faifortrading-2edd6fac689d) - Boris Banushev (2019)\n* [RNN and LSTM — The Neural Networks with Memory](https:\u002F\u002Flevelup.gitconnected.com\u002Frnn-and-lstm-the-neural-networks-with-memory-24e4cb152d1b) - Nagesh Singh Chauhan (2020)\n* [Introduction to Deep Learning Trading in Hedge Funds](https:\u002F\u002Fwww.toptal.com\u002Fdeep-learning\u002Fdeep-learning-trading-hedge-funds) - Neven Pičuljan\n","# 令人惊叹的深度交易\n[![Awesome](https:\u002F\u002Fcdn.rawgit.com\u002Fsindresorhus\u002Fawesome\u002Fd7305f38d29fed78fa85652e3a63e154dd8e8829\u002Fmedia\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsindresorhus\u002Fawesome)\n\n用于将人工智能\u002F深度学习\u002F机器学习\u002F神经网络应用于算法交易的代码、论文和资源列表。\n\n开放获取：任何人可在您选择的免费 MIT 许可证或知识共享 CC-BY 国际公共许可证下，以任何方式免费使用和再利用这些内容，且不需支付任何费用。\n\n© 2021 克雷格·贝尔斯 ([@cbailes](https:\u002F\u002Fgithub.com\u002Fcbailes) | [Patreon](https:\u002F\u002Fwww.patreon.com\u002Fcraigbailes) | [contact@craigbailes.com](mailto:contact@craigbailes.com))\n\n# 目录\n- [论文](#papers)\n  * [元分析与系统综述](#meta-analyses--systematic-reviews)\n  * [卷积神经网络 (CNNs)](#convolutional-neural-networks-cnns)\n  * [长短期记忆网络 (LSTMs)](#long-short-term-memory-lstms)\n  * [生成对抗网络 (GANs)](#generative-adversarial-networks-gans)\n  * [高频交易](#high-frequency)\n  * [投资组合](#portfolio)\n  * [强化学习](#reinforcement-learning)\n  * [漏洞](#vulnerabilities)\n  * [加密货币](#cryptocurrency)\n  * [社交处理](#social-processing)\n    + [行为分析](#behavioral-analysis)\n    + [情感分析](#sentiment-analysis)\n- [仓库](#repositories)\n  * [生成对抗网络 (GANs)](#generative-adversarial-networks-gans-1)\n  * [指南](#guides)\n  * [加密货币](#cryptocurrency-1) \n  * [数据集](#datasets)\n    + [仿真](#simulation)\n- [资源](#resources)\n  * [演示文稿](#presentations)\n  * [课程](#courses)\n  * [延伸阅读](#further-reading)\n\n# 论文\n\n* [基于分类的金融市场预测：深度神经网络的应用](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1603.08604) - 马修·迪克森、迭戈·克拉布扬、金勋邦（2016年）\n* [限价订单簿的深度学习方法](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1601.01987) - 贾斯汀·西里格纳诺（2016年）\n* [基于深度神经网络的高频交易策略](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007%2F978-3-319-42297-8_40) - 安德烈斯·阿雷瓦洛、海梅·尼诺、赫尔曼·埃尔南德斯、哈维尔·桑多瓦尔（2016年）\n* [用于金融投资组合管理问题的深度强化学习框架](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1706.10059) - 蒋正尧、徐迪兴、梁锦俊（2017年）\n* [基于循环强化学习和LSTM神经网络的智能交易代理](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1707.07338.pdf) - 大卫·W·卢（2017年）\n* [深度对冲策略](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1802.03042) - 汉斯·比勒、卢卡斯·戈农、约瑟夫·泰希曼、本·伍德（2018年）\n* [基于深度强化学习的股票交易机器人](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-981-10-8201-6_5) - 阿希尔·拉杰·阿齐科丹、安维塔·G·K·巴特、玛玛塔·V·贾达夫（2018年）\n* [将金融交易视为游戏：一种深度强化学习方法](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1807.02787) - 黄建义（2018年）\n* [股票交易的实用深度强化学习方法](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1811.07522) - 熊卓然、刘晓阳、钟山、杨洪洋、安瓦尔·瓦利德（2018年）\n* [基于GPU的算法交易与机器学习](http:\u002F\u002Fceur-ws.org\u002FVol-2147\u002Fp09.pdf) - 曼塔斯·瓦伊托尼斯、绍柳斯·马斯特凯卡、康斯坦蒂纳斯·科罗夫基纳斯（2018年）\n* [利用深度卷积神经网络的量化交易方法](https:\u002F\u002Fiopscience.iop.org\u002Farticle\u002F10.1088\u002F1757-899X\u002F490\u002F4\u002F042018\u002Fpdf) - 陈海波、梁道磊、LL·赵（2019年）\n* [交易所市场中的深度学习](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0167624518300702) - 瑞·贡萨尔维斯、维托尔·米格尔·里贝罗、费尔南多·洛博·佩雷拉、安娜·保拉·罗沙（2019年）\n* [基于股票K线图时间序列的深度卷积神经网络金融交易模型](https:\u002F\u002Farxiv.org\u002Fabs\u002F1903.04610) - 奥默·贝拉特·塞泽尔、艾哈迈德·穆拉特·厄兹巴约卢（2019年）\n* [基于价格跟踪的金融交易深度强化学习](https:\u002F\u002Fieeexplore.ieee.org\u002Fdocument\u002F8683161) - 康斯坦提诺斯·赛塔斯·扎尔基亚斯、尼古拉奥斯·帕萨利斯、阿夫拉姆·赞特基迪斯、阿纳斯塔西奥斯·特法斯（2019年）\n* [用于剥头皮交易的多智能体合作强化学习框架](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.00441) - 岳助、曹泰贤、金万俊、尹一柱、李东锡、李承浩（2019年）\n* [利用深度Q学习改进金融交易决策：预测股票数量、行动策略及迁移学习](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS0957417418306134) - 郑姬恩、金夏英（2019年）\n* [深度执行——基于价值与策略的强化学习，用于交易并超越市场基准](https:\u002F\u002Fpapers.ssrn.com\u002Fsol3\u002Fpapers.cfm?abstract_id=3374766) - 凯文·达贝里乌斯、埃尔文·格拉纳特、帕特里克·卡尔松（2019年）\n* [股票日间交易策略中机器学习算法的实证研究](https:\u002F\u002Fwww.hindawi.com\u002Fjournals\u002Fmpe\u002F2019\u002F7816154\u002Fref\u002F) - 吕东东、袁书涵、李美姿、杨翔（2019年）\n* [机器学习量化交易指南](http:\u002F\u002Fdx.doi.org\u002F10.2139\u002Fssrn.3232143) - 丹尼尔·亚历山大·布洛赫（2019年）\n* [探索利用深度学习改进动量策略的可能性](http:\u002F\u002Fhdl.handle.net\u002F2105\u002F49940) - 亚当·塔卡茨、X·萧（2019年）\n* [利用深度神经网络增强时间序列动量策略](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.04912) - 布赖恩·林、斯特凡·佐伦、斯蒂芬·罗伯茨（2019年）\n* [用于清算策略分析的多智能体深度强化学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.11046) - 包文航、刘晓阳（2019年）\n* [基于深度学习的特征工程在股价走势预测中的应用](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0950705118305264) - 温龙、陆志晨、崔凌霄（2019年）\n* [股票市场预测与分析综述](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340583328_Review_on_Stock_Market_Forecasting_Analysis-LSTM_Long-Short_Term_Memory_Holt's_Seasonal_MethodANN_Artificial_Neural_Network_ARIMA_Auto_Regressive_Integrated_Minimum_Average_PCA_MLP_Multi_Layers_Percep) - 阿尼尔班·巴尔、德巴扬·冈古利、金舒克·查特吉（2019年）\n* [神经网络作为俄罗斯金融市场数字化背景下的预测工具](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340474330_Neural_Networks_as_a_Forecasting_Tool_in_the_Context_of_the_Russian_Financial_Market_Digitalization) - 瓦列里·阿列欣、奥列格·斯维里多夫、因娜·涅克拉索娃、德米特里·谢甫琴科（2020年）\n* [多源驱动的量化投资深度层次化策略模型](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8743385) - 唐春明、朱文燕、于翔（2019年）\n* [在BSE100中寻找高效股票：巴菲特方法的实施导论](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340501895_Asian_Journal_of_Management_Finding_Efficient_Stocks_in_BSE100_Implementation_of_Buffet_Approach_INTRODUCTION) - 谢琳·瓦尔盖斯、桑迪普·塔库尔、梅达·丁格拉（2020年）\n* [资产定价中的深度学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.00745) - 陈路阳、马库斯·佩尔格、杰森·朱（2020年）\n\n## 元分析与系统综述\n* [机器学习在股票交易中的应用：综述](http:\u002F\u002Fdx.doi.org\u002F10.14419\u002Fijet.v7i2.33.15479) - 科克·盛·谭、拉贾斯瓦兰·洛格斯瓦兰（2018年）\n* [评估机器学习算法在金融市场预测中的表现：全面综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F1906.07786) - 卢卡斯·瑞尔、塞巴斯蒂安·赛登斯（2019年）\n* [金融市场中的强化学习](https:\u002F\u002Fwww.mdpi.com\u002F2306-5729\u002F4\u002F3\u002F110\u002Fpdf) - 特里·凌泽·孟、马特鲁布·胡什（2019年）\n* [深度学习在金融时间序列预测中的应用：2005—2019年系统文献综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.13288) - 奥默·贝拉特·塞泽尔、穆罕默德·乌古尔·古德莱克、艾哈迈德·穆拉特·厄兹巴约卢（2019年）\n* [股票市场预测中基本面和技术分析的系统综述](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F335274959_A_systematic_review_of_fundamental_and_technical_analysis_of_stock_market_predictions) - 艾萨克·科菲·恩蒂、阿德巴约·阿德科亚、本杰明·阿苏巴姆·韦约里（2019年）\n\n## 卷积神经网络（CNNs）\n* [基于深度学习的股票交易模型：二维卷积神经网络趋势检测](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F323131323_A_deep_learning_based_stock_trading_model_with_2-D_CNN_trend_detection) - Ugur Gudelek、S. Arda Boluk、Murat Ozbayoglu、Murat Ozbayoglu（2017年）\n* [基于深度卷积神经网络的算法化金融交易：时间序列转图像方法](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F324802031_Algorithmic_Financial_Trading_with_Deep_Convolutional_Neural_Networks_Time_Series_to_Image_Conversion_Approach) - Omer Berat Sezar、Murat Ozbayoglu（2018年）\n* [DeepLOB：用于限价订单簿的深度卷积神经网络](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F8673598) - Zihao Zhang、Stefan Zohren、Stephen Roberts（2019年）\n\n## 长短期记忆网络（LSTMs）\n* [斯坦福CS229课程：深度学习在算法交易中的应用](http:\u002F\u002Fcs229.stanford.edu\u002Fproj2017\u002Ffinal-reports\u002F5241098.pdf) - Guanting Chen、Yatong Chen、Takahiro Fushimi（2017年）\n* [基于深度学习模型的股票价格预测](https:\u002F\u002Farxiv.org\u002Fabs\u002F1909.12227) - Jialin Liu、Fei Chao、Yu-Chen Lin、Chih-Min Lin（2019年）\n* [深度学习在股市交易中的应用：一种更优的交易策略吗？](https:\u002F\u002Fdoi.org\u002F10.14311\u002FNNW.2019.29.011) - D. Fister、J. C. Mun、V. Jagrič、T. Jagrič（2019年）\n* [循环神经网络在股市短期投资决策中的性能评估](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F339751012_Performance_Evaluation_of_Recurrent_Neural_Networks_for_Short-Term_Investment_Decision_in_Stock_Market) - Alexandre P. da Silva、Silas S. L. Pereira、Mário W. L. Moreira、Joel J. P. C. Rodrigues、Ricardo A. L. Rabêlo、Kashif Saleem（2020年）\n* [基于LSTM神经网络的金融资产交易预测模型研究](https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs00521-020-04992-7) - Xue Yan、Wang Weihan、Miao Chang（2020年）\n* [利用长短期记忆神经网络模型预测波段交易的股票走势](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F340789607_Prediction_Of_Stock_Trend_For_Swing_Trades_Using_Long_Short-Term_Memory_Neural_Network_Model) - Varun Totakura、V. Devasekhar、Madhu Sake（2020年）\n* [一种新颖的深度学习框架：基于CEEMD和LSTM的金融时间序列预测与分析](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0957417420304334) - Yong'an Zhang、Binbin Yan、Memon Aasma（2020年）\n* [深度股票预测](https:\u002F\u002Farxiv.org\u002Fabs\u002F2006.04992) - Akash Doshi、Alexander Issa、Puneet Sachdeva、Sina Rafati、Somnath Rakshit（2020年）\n\n## 生成对抗网络（GANs）\n* [生成对抗网络在金融交易策略调优与组合中的应用](https:\u002F\u002Fdeepai.org\u002Fpublication\u002Fgenerative-adversarial-networks-for-financial-trading-strategies-fine-tuning-and-combination) - Adriano Koshiyama（2019年）\n* [基于生成对抗网络的股市预测](https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.procs.2019.01.256) - Kang Zhang、Guoqiang Zhong、Junyu Dong、Shengke Wang、Yong Wang（2019年）\n* [用于股市价格预测的生成对抗网络](https:\u002F\u002Fcs230.stanford.edu\u002Fprojects_fall_2019\u002Freports\u002F26259829.pdf) - Ricardo Alberto Carrillo Romero（2019年）\n* [用于市场分时识别的生成对抗网络](https:\u002F\u002Fmpra.ub.uni-muenchen.de\u002Fid\u002Feprint\u002F99846) - Luca Grilli、Domenico Santoro（2020年）\n\n## 高频交易\n* [基于深度神经网络的高频数据算法交易](https:\u002F\u002Flink.springer.com\u002Fchapter\u002F10.1007\u002F978-3-319-66963-2_14) - Andrés Arévalo、Jaime Niño、German Hernandez、Javier Sandoval、Diego León、Arbey Aragón（2017年）\n* [基于生成对抗网络的高频数据股市预测](https:\u002F\u002Fdoi.org\u002F10.1155\u002F2018\u002F4907423) - Xingyu Zhou、Zhisong Pan、Guyu Hu、Siqi Tang、Cheng Zhao（2018年）\n* [深度神经网络在高频交易中的应用](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.01506) - Prakhar Ganesh、Puneet Rakheja（2018年）\n* [机器学习在股票高频交易中的应用](https:\u002F\u002Fwww.ijser.org\u002Fresearchpaper\u002FApplication-of-Machine-Learning-in-High-Frequency-Trading-of-Stocks.pdf) - Obi Bertrand Obi（2019年）\n\n## 投资组合\n* [基于深度强化学习的人工智能多场景财务规划](https:\u002F\u002Fpapers.ssrn.com\u002Fsol3\u002Fpapers.cfm?abstract_id=3516480) - Gordon Irlam（2020年）\n* [G-Learner和GIRL：基于强化学习的目标导向财富管理](https:\u002F\u002Farxiv.org\u002Fabs\u002F2002.10990) - Matthew Dixon、Igor Halperin（2020年）\n* [基于强化学习的投资组合管理：结合增强型资产变动预测状态](https:\u002F\u002Fwww.aaai.org\u002FPapers\u002FAAAI\u002F2020GB\u002FAAAI-YeY.4483.pdf) - Yunan Ye、Hengzhi Pei、Boxin Wang、Pin-Yu Chen、Yada Zhu、Jun Xiao、Bo Li（2020年）\n\n## 强化学习\n* [金融市场中的强化学习——综述](http:\u002F\u002Fhdl.handle.net\u002F10419\u002F183139) - Thomas G. Fischer（2018年）\n* [AlphaStock：基于可解释深度强化注意力网络的“买赢家、卖输家”投资策略](https:\u002F\u002Farxiv.org\u002Fabs\u002F1908.02646) - Jingyuan Wang、Yang Zhang、Ke Tang、Junjie Wu、Zhang Xiong（2019年）\n* [捕捉金融市场以应用深度强化学习](https:\u002F\u002Farxiv.org\u002Fabs\u002F1907.04373) - Souradeep Chakraborty（2019年）\n* [强化学习在外汇交易中的应用](http:\u002F\u002Fstanford.edu\u002Fclass\u002Fmsande448\u002F2019\u002FFinal_reports\u002Fgr2.pdf) - Yuqin Dai、Chris Wang、Iris Wang、Yilun Xu（2019年）\n* [深度强化学习在算法交易中的应用](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.06627) - Thibaut Théate、Damien Ernst（2020年）\n* [单资产交易：一种基于循环强化学习的方法](http:\u002F\u002Furn.kb.se\u002Fresolve?urn=urn:nbn:se:mdh:diva-47505) - Marko Nikolic（2020年）\n* [利用深度强化学习击败中国股市](https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FHuang_Gang9\u002Fpublication\u002F340438304_Beat_China's_stock_market_by_using_Deep_reinforcement_learning\u002Flinks\u002F5e88e007299bf130797c7a68\u002FBeat-Chinas-stock-market-by-using-Deep-reinforcement-learning.pdf) - Gang Huang、Xiaohua Zhou、Qingyang Song（2020年）\n* [基于烛台分解特征的深度强化学习自适应金融交易系统](https:\u002F\u002Fdoi.org\u002F10.1109\u002FACCESS.2020.2982662) - Ding Fengqian、Luo Chao（2020年）\n* [深度Q网络在投资组合管理中的应用](https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.06365) - Ziming Gao、Yuan Gao、Yi Hu、Zhengyong Jiang、Jionglong Su（2020年）\n* [基于双深度Q网络的深度强化学习配对交易](https:\u002F\u002Fieeexplore.ieee.org\u002Fabstract\u002Fdocument\u002F9031159) - Andrew Brim（2020年）\n* [基于奖励修正的量化选股强化学习模型](https:\u002F\u002Fdoi.org\u002F10.1088\u002F1757-899X\u002F768\u002F7\u002F072036) - Haibo Chen、Chenyu Zhang、Yunke Li（2020年）\n* [AAMDRL：基于深度强化学习的增强型资产管理](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.08497) - Eric Benhamou、David Saltiel、Sandrine Ungari、Abhishek Mukhopadhyay、Jamal Atif（2020年）\n\n## 指南\n* [使用堆叠 LSTM 进行股票价格预测与 forecasting —— 深度学习](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=H6du_pfuznE) - Krish Naik (2020) \n* [时间序列 forecasting 中 ARIMA 模型与 LSTM RNN 模型的比较](https:\u002F\u002Fanalyticsindiamag.com\u002Fcomparing-arima-model-and-lstm-rnn-model-in-time-series-forecasting\u002F) - Vaibhav Kumar (2020)\n* [LSTM 用于预测道琼斯工业平均指数：一种时间序列 forecasting 模型](https:\u002F\u002Fmedium.com\u002Fanalytics-vidhya\u002Flstm-to-predict-dow-jones-industrial-average-time-series-647b0115f28c) - Sarit Maitra (2020)\n\n## 漏洞\n* [深度算法交易策略的对抗攻击](https:\u002F\u002Farxiv.org\u002Fabs\u002F2010.11388) - Yaser Faghan, Nancirose Piazza, Vahid Behzadan, Ali Fathi (2020)\n\n## 加密货币\n* [基于深度强化学习方法推荐加密货币交易点](https:\u002F\u002Fdoi.org\u002F10.3390\u002Fapp10041506) - Otabek Sattarov, Azamjon Muminov, Cheol Won Lee, Hyun Kyu Kang, Ryumduck Oh, Junho Ahn, Hyung Jun Oh, Heung Seok Jeon (2020)\n\n## 社会处理\n### 行为分析\n* [深度学习能否预测高风险散户投资者？—— 金融风险行为 forecasting 的案例研究](https:\u002F\u002Fwww.researchgate.net\u002Fpublication\u002F329734839_Can_Deep_Learning_Predict_Risky_Retail_Investors_A_Case_Study_in_Financial_Risk_Behavior_Forecasting) - Yaodong Yang, Alisa Kolesnikova, Stefan Lessmann, Tiejun Ma, Ming-Chien Sung, Johnnie E.V. Johnson (2019)\n* [基于深度学习的投资者行为监测](https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Ffull\u002F10.1080\u002F0144929X.2020.1717627?casa_token=heptguQeb3kAAAAA%3AB1D3L4udpW0l3nw0sJHSpZ9tvDjptW3HfDqa_3XrUS-9owFARbHnurpSdtCy54KzR05aTdNTwhbnMA) - Song Wang, Xiaoguang Wang, Fanglin Meng, Rongjun Yang, Yuanjun Zhao (2020)\n\n### 情感分析\n* [利用深度学习改进决策 analytics：以财务信息披露为例](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1508.01993) - Stefan Feuerriegel, Ralph Fehrer (2015)\n* [大数据：用于金融情感分析的深度学习](https:\u002F\u002Fjournalofbigdata.springeropen.com\u002Farticles\u002F10.1186\u002Fs40537-017-0111-6) - Sahar Sohangir, Dingding Wang, Anna Pomeranets, Taghi M. Khoshgoftaar (2018)\n* [使用机器学习预测股票价格](https:\u002F\u002Fmedium.com\u002Fanalytics-vidhya\u002Fusing-machine-learning-to-predict-stock-prices-c4d0b23b029a) - Vivek Palaniappan (2018)\n* [利用 Twitter 进行股票预测](https:\u002F\u002Ftowardsdatascience.com\u002Fstock-prediction-using-twitter-e432b35e14bd) - Khan Saad Bin Hasan (2019)\n* [基于情感和知识的深度强化学习算法交易](https:\u002F\u002Farxiv.org\u002Fabs\u002F2001.09403) - Abhishek Nan, Anandh Perumal, Osmar R. Zaiane (2020)\n\n# 仓库\n* [Yvictor\u002FTradingGym](https:\u002F\u002Fgithub.com\u002FYvictor\u002FTradingGym) - 用于训练强化学习智能体或简单规则基础算法的交易和回测环境\n* [Rachnog\u002FDeep-Trading](https:\u002F\u002Fgithub.com\u002FRachnog\u002FDeep-Trading) - 实验性时间序列 forecasting\n* [jobvisser03\u002Fdeep-trading-advisor](https:\u002F\u002Fgithub.com\u002Fjobvisser03\u002Fdeep-trading-advisor) - Deep Trading Advisor 使用 MLP、CNN 和 RNN+LSTM，结合 Keras、zipline、Dash 和 Plotly\n* [rosdyana\u002FCNN-Financial-Data](https:\u002F\u002Fgithub.com\u002Frosdyana\u002FCNN-Financial-Data) - 使用卷积神经网络进行深度交易\n* [iamSTone\u002FDeep-trader-CNN-kospi200futures](https:\u002F\u002Fgithub.com\u002FiamSTone\u002FDeep-trader-CNN-kospi200futures) - 使用 CNN 预测 Kospi200 指数期货\n* [ha2emnomer\u002FDeep-Trading](https:\u002F\u002Fgithub.com\u002Fha2emnomer\u002FDeep-Trading) - 基于 Keras 的 LSTM RNN \n* [gujiuxiang\u002FDeep_Trader.pytorch](https:\u002F\u002Fgithub.com\u002Fgujiuxiang\u002FDeep_Trader.pytorch) - 该项目在股票市场中使用强化学习，智能体尝试学习交易。基于 PyTorch。\n* [ZhengyaoJiang\u002FPGPortfolio](https:\u002F\u002Fgithub.com\u002FZhengyaoJiang\u002FPGPortfolio) - PGPortfolio：策略梯度投资组合，是“用于金融投资组合管理问题的深度强化学习框架”的源代码\n* [yuriak\u002FRLQuant](https:\u002F\u002Fgithub.com\u002Fyuriak\u002FRLQuant) - 将强化学习应用于量化交易（策略梯度，直接 RL）\n* [ucaiado\u002FQLearning_Trading](https:\u002F\u002Fgithub.com\u002Fucaiado\u002FQLearning_Trading) - 使用 Q-Learning 进行交易\n* [laikasinjason\u002Fdeep-q-learning-trading-system-on-hk-stocks-market](https:\u002F\u002Fgithub.com\u002Flaikasinjason\u002Fdeep-q-learning-trading-system-on-hk-stocks-market) - 在香港证券交易所实施深度 Q 学习\n* [golsun\u002Fdeep-RL-trading](https:\u002F\u002Fgithub.com\u002Fgolsun\u002Fdeep-RL-trading) - Xiang Gao 论文“时间序列的深度强化学习：玩理想化的交易游戏”的代码库\n* [huseinzol05\u002FStock-Prediction-Models](https:\u002F\u002Fgithub.com\u002Fhuseinzol05\u002FStock-Prediction-Models) - 收集了用于股票 forecasting 的机器学习和深度学习模型，包括交易机器人和模拟\n* [jiewwantan\u002FStarTrader](https:\u002F\u002Fgithub.com\u002Fjiewwantan\u002FStarTrader) - 使用深度强化学习算法训练智能体像人类一样交易：深度确定性策略梯度（DDPG）学习算法\n* [notadamking\u002FRLTrader](https:\u002F\u002Fgithub.com\u002Fnotadamking\u002FRLTrader) - 一个使用深度强化学习和 OpenAI gym 的加密货币交易环境\n\n## 生成对抗网络 (GANs)\n* [borisbanushev\u002Fstockpredictionai](https:\u002F\u002Fgithub.com\u002Fborisbanushev\u002Fstockpredictionai) - 一个笔记本，用于使用 LSTM 生成器和 CNN 判别器预测股票价格走势\n* [kah-ve\u002FMarketGAN](https:\u002F\u002Fgithub.com\u002Fkah-ve\u002FMarketGAN) - 在股票市场上实现生成对抗网络\n\n## 加密货币\n* [samre12\u002Fdeep-trading-agent](https:\u002F\u002Fgithub.com\u002Fsamre12\u002Fdeep-trading-agent) - 基于深度强化学习的比特币交易智能体，使用 DeepSense Network 近似 Q 函数。\n* [ThirstyScholar\u002Ftrading-bitcoin-with-reinforcement-learning](https:\u002F\u002Fgithub.com\u002FThirstyScholar\u002Ftrading-bitcoin-with-reinforcement-learning) - 使用强化学习交易比特币\n* [lefnire\u002Ftforce_btc_trader](https:\u002F\u002Fgithub.com\u002Flefnire\u002Ftforce_btc_trader) - 一个基于 TensorForce 的比特币交易机器人（algo-trader）。使用深度强化学习根据价格历史自动买入\u002F卖出\u002F持有 BTC。\n\n## 数据集\n* [kaggle\u002F庞大的股票市场数据集](https:\u002F\u002Fwww.kaggle.com\u002Fborismarjanovic\u002Fprice-volume-data-for-all-us-stocks-etfs) - 美国所有股票和 ETF 的历史每日价格和成交量\n* [Alpha Vantage](https:\u002F\u002Fwww.alphavantage.co\u002F) - 免费的 JSON 和 CSV 格式 API，实时和历史股票数据、外汇和加密货币行情，50 多种技术指标  \n* [Quandl](https:\u002F\u002Fquandl.com\u002F)\n\n### 模拟\n* [生成逼真的股票市场订单流](https:\u002F\u002Fopenreview.net\u002Fpdf?id=rke41hC5Km) - 匿名作者 (2018)\n* [深度对冲：学习模拟股票期权市场](https:\u002F\u002Farxiv.org\u002Fabs\u002F1911.01700) - Magnus Wiese、Lianjun Bai、Ben Wood、Hans Buehler (2019)\n\n# 资源\n\n## 演讲\n* [BigDataFinance 神经网络简介](http:\u002F\u002Fbigdatafinance.eu\u002Fwp\u002Fwp-content\u002Fuploads\u002F2016\u002F06\u002FTefas_BigDataFinanceNeuralNetworks_Intro_Web.pdf) - 阿纳斯塔西奥斯·特法斯，塞萨洛尼基亚里士多德大学助理教授（2016年）\n* [利用深度学习进行交易：动机、挑战与解决方案](http:\u002F\u002Fon-demand.gputechconf.com\u002Fgtc-il\u002F2017\u002Fpresentation\u002Fsil7121-yam-peleg-deep-learning-for-high-frequency-trading%20(2).pdf) - 亚姆·佩莱格，GPU 技术大会（2017年）\n* [金融科技、人工智能与金融中的机器学习](https:\u002F\u002Fwww.slideshare.net\u002Fsanjivdas\u002Ffintech-ai-machine-learning-in-finance) - 桑吉夫·达斯（2018年）\n* [用于投资组合优化的深度残差学习：结合注意力机制与切换模块](https:\u002F\u002Fengineering.nyu.edu\u002Fsites\u002Fdefault\u002Ffiles\u002F2019-03\u002FNYU%20FRE%20Seminar-Jifei%20Wang%20%28slides%29.pdf) - 杰夫·王，纽约大学博士\n\n## 课程\n* [Udacity 的 ND880 人工智能交易纳米学位课程](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Fai-for-trading--nd880)（+[GitHub 代码仓库](https:\u002F\u002Fgithub.com\u002Fudacity\u002Fartificial-intelligence-for-trading)）\n* [Quantra 平台埃内斯特·P·陈博士开设的交易中的神经网络课程](https:\u002F\u002Fquantra.quantinsti.com\u002Fcourse\u002Fneural-networks-deep-learning-trading-ernest-chan)\n* [纽约大学在 Coursera 上推出的金融领域的机器学习与强化学习专项课程](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fmachine-learning-reinforcement-finance)\n\n## 聚会\n* [Meetup 上的人工智能与算法交易聚会](https:\u002F\u002Fwww.meetup.com\u002FArtificial-Intelligence-in-Finance-Algorithmic-Trading\u002F)（纽约市）\n\n## 更多阅读\n* [用于算法交易的神经网络：简单的时间序列预测](https:\u002F\u002Fmedium.com\u002F@alexrachnog\u002Fneural-networks-for-algorithmic-trading-part-one-simple-time-series-forecasting-f992daa1045a) - 亚历克斯·拉赫诺格（2016年）\n* [利用深度学习预测加密货币价格](https:\u002F\u002Fdashee87.github.io\u002Fdeep%20learning\u002Fpython\u002Fpredicting-cryptocurrency-prices-with-deep-learning\u002F) - 大卫·希恩（2017年）\n* [强化学习入门：如何通过强化学习学会交易](http:\u002F\u002Fwww.wildml.com\u002F2018\u002F02\u002Fintroduction-to-learning-to-trade-with-reinforcement-learning\u002F) - 丹尼·布里茨（2018年）\n* [网络研讨会：如何使用深度神经网络预测股票价格](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RMh8AUTQWQ8) - 埃雷兹·卡茨，Lucena Research（2018年）\n* [打造不会亏钱的比特币交易机器人](https:\u002F\u002Ftowardsdatascience.com\u002Fcreating-bitcoin-trading-bots-that-dont-lose-money-2e7165fb0b29) - 亚当·金（2019年）\n* [为什么深度强化学习可以帮助提高交易效率](https:\u002F\u002Fmedium.com\u002F@viktortachev\u002Fwhy-deep-reinforcement-learning-can-help-improve-trading-efficiency-5af57e8faf9d) - 维克托·塔切夫（2019年）\n* [利用最先进技术优化深度学习交易机器人](https:\u002F\u002Ftowardsdatascience.com\u002Fusing-reinforcement-learning-to-trade-bitcoin-for-massive-profit-b69d0e8f583b) - 亚当·金（2019年）\n* [运用深度学习最新进展预测股价走势](https:\u002F\u002Ftowardsdatascience.com\u002Faifortrading-2edd6fac689d) - 鲍里斯·巴努舍夫（2019年）\n* [RNN 与 LSTM — 具有记忆功能的神经网络](https:\u002F\u002Flevelup.gitconnected.com\u002Frnn-and-lstm-the-neural-networks-with-memory-24e4cb152d1b) - 纳盖什·辛格·乔汉（2020年）\n* [对冲基金中的深度学习交易入门](https:\u002F\u002Fwww.toptal.com\u002Fdeep-learning\u002Fdeep-learning-trading-hedge-funds) - 内文·皮丘良","# awesome-deep-trading 快速上手指南\n\n`awesome-deep-trading` 并非一个可直接安装运行的单一软件包或框架，而是一个**精选资源列表**，汇集了应用于算法交易的 AI\u002F深度学习代码库、学术论文及相关资料。本指南将指导开发者如何利用该列表快速构建自己的量化交易研究环境。\n\n## 环境准备\n\n由于列表中的项目多基于 Python 生态和主流深度学习框架，建议按以下标准配置开发环境：\n\n*   **操作系统**：Linux (Ubuntu 20.04+ 推荐), macOS, 或 Windows (建议使用 WSL2)。\n*   **Python 版本**：3.8 - 3.10 (多数金融深度学习项目对此范围支持最佳)。\n*   **核心依赖**：\n    *   `PyTorch` 或 `TensorFlow` (根据具体选用的仓库决定)\n    *   `pandas`, `numpy` (数据处理)\n    *   `scikit-learn` (传统机器学习辅助)\n    *   `gym` 或 `gymnasium` (强化学习环境)\n*   **硬件要求**：若复现涉及 CNN、LSTM 或 GAN 的论文（尤其是高频交易部分），强烈建议使用支持 CUDA 的 NVIDIA GPU。\n\n## 安装步骤\n\n由于这是一个资源索引库，您不需要安装 `awesome-deep-trading` 本身，而是需要克隆该仓库以获取文献链接和代码库索引，然后选择具体的子项目进行安装。\n\n### 1. 克隆资源索引库\n首先获取该列表的本地副本，以便查阅论文和对应的 GitHub 仓库链接。\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fcbailes\u002Fawesome-deep-trading.git\ncd awesome-deep-trading\n```\n\n### 2. 配置通用深度学习环境\n在运行列表中任何具体的代码仓库前，建议创建一个隔离的虚拟环境并安装基础科学计算库。\n\n**创建虚拟环境：**\n```bash\npython -m venv venv\nsource venv\u002Fbin\u002Factivate  # Linux\u002FmacOS\n# 或在 Windows 上: venv\\Scripts\\activate\n```\n\n**安装基础依赖（使用国内镜像源加速）：**\n```bash\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple numpy pandas matplotlib scikit-learn\n```\n\n**安装深度学习框架（按需选择其一）：**\n\n*   **PyTorch (推荐，社区资源较多):**\n    ```bash\n    pip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118\n    ```\n*   **TensorFlow:**\n    ```bash\n    pip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple tensorflow\n    ```\n\n### 3. 获取具体项目代码\n浏览 `README.md` 中的 **[Repositories](#repositories)** 章节，找到感兴趣的项目（例如某个基于 GAN 或 LSTM 的交易机器人），进入其对应的 GitHub 页面进行克隆和安装。\n\n*示例：假设你选择了列表中某个名为 `deep-trading-bot` 的仓库（此处为示意）：*\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fauthor\u002Fdeep-trading-bot.git\ncd deep-trading-bot\npip install -r requirements.txt\n```\n\n## 基本使用\n\n使用 `awesome-deep-trading` 的核心工作流是：**检索论文\u002F代码 -> 复现策略 -> 回测验证**。\n\n### 1. 检索策略与论文\n打开本地的 `README.md` 文件，根据需求查找对应类别的资源：\n*   **趋势预测**：查看 [Convolutional Neural Networks (CNNs)](#convolutional-neural-networks-cnns) 或 [Long Short-Term Memory (LSTMs)](#long-short-term-memory-lstms) 章节。\n*   **生成数据\u002F增强策略**：查看 [Generative Adversarial Networks (GANs)](#generative-adversarial-networks-gans) 章节。\n*   **自动决策**：查看 [Reinforcement Learning](#reinforcement-learning) 章节。\n*   **高频交易**：查看 [High Frequency](#high-frequency) 章节。\n\n点击列表中的论文标题（如 *[Classification-based Financial Markets Prediction using Deep Neural Networks]*）阅读 arXiv 原文，理解模型架构。\n\n### 2. 运行示例代码\n大多数列出的仓库都包含训练脚本。以下是一个典型的基于 PyTorch 的训练流程示例（具体命令需参考所选子项目的文档）：\n\n```python\n# 伪代码示例：加载数据并训练模型\nimport torch\nfrom model import TradingLSTM  # 假设从选定仓库导入\nfrom data_loader import get_market_data\n\n# 1. 准备数据\ndataset = get_market_data(symbol='BTC-USDT', timeframe='1h')\n\n# 2. 初始化模型\nmodel = TradingLSTM(input_size=10, hidden_size=50, num_layers=2)\n\n# 3. 训练循环\nfor epoch in range(100):\n    loss = model.train_step(dataset)\n    if epoch % 10 == 0:\n        print(f\"Epoch {epoch}, Loss: {loss.item()}\")\n```\n\n### 3. 数据集获取\n在 [Datasets](#datasets) 章节中查找适用的金融时间序列数据。许多项目会使用 `yfinance` 或加密货币交易所 API 获取实时数据，部分高级项目可能需要特定的订单簿（Limit Order Book）数据集。\n\n```bash\n# 示例：使用 Python 快速获取股票数据用于测试\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple yfinance\n```\n\n```python\nimport yfinance as yf\ndata = yf.download(\"AAPL\", start=\"2020-01-01\", end=\"2023-01-01\")\nprint(data.head())\n```\n\n通过结合本列表提供的理论依据（论文）和工程实现（代码仓库），您可以快速搭建并验证自己的深度量化交易策略。","某量化初创团队正试图构建基于深度强化学习的加密货币自动交易系统，但在技术选型和论文复现阶段陷入停滞。\n\n### 没有 awesome-deep-trading 时\n- **资源检索低效**：团队成员需在 arXiv、IEEE 等各大数据库中海量搜索\"Deep Reinforcement Learning Trading\"相关论文，耗时数周仍难以覆盖最新成果。\n- **复现门槛极高**：找到的论文往往缺乏配套代码或关键参数说明，导致如 LSTM 网络结构或奖励函数设计等核心逻辑无法落地验证。\n- **知识体系碎片化**：缺乏对 CNN、GAN 及高频交易策略的系统性分类，团队难以判断哪种模型更适合当前的波动性市场，容易选错技术路线。\n- **数据获取困难**：找不到经过清洗的高质量模拟数据集或回测环境，自行构建数据清洗管道占用了大量本应用于模型优化的开发时间。\n\n### 使用 awesome-deep-trading 后\n- **一站式精准导航**：直接利用其分类目录（如“强化学习”、“加密货币”板块），在几分钟内锁定了 Jiang (2017) 和 Huang (2018) 等几篇高价值奠基性论文。\n- **代码与理论对接**：通过关联的 Repositories 章节，快速找到了论文对应的开源实现和指南，大幅降低了从理论公式到 Python 代码的转化难度。\n- **技术路线清晰**：借助 Meta Analyses 和系统性综述，团队迅速对比了不同神经网络在金融时序数据上的优劣，果断确定了以 PPO 算法为核心的交易策略。\n- **数据环境就绪**：直接采用了列表中推荐的仿真数据集和回测框架，将原本需要两周的数据准备工作压缩至两天，加速了模型迭代周期。\n\nawesome-deep-trading 通过将分散的学术成果与工程资源结构化整合，帮助开发者跨越了从理论研究到实盘策略落地的巨大鸿沟。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fcbailes_awesome-deep-trading_8eab2189.png","cbailes","Craig Bailes","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fcbailes_62c4d4fd.jpg",null,"Founder @Botomate ","United States","contact@craigbailes.com","https:\u002F\u002Fcraigbailes.com","https:\u002F\u002Fgithub.com\u002Fcbailes",1863,334,"2026-04-18T03:22:35","MIT",5,"","未说明",{"notes":89,"python":87,"dependencies":90},"该项目是一个资源列表（Awesome List），汇集了应用于算法交易的 AI\u002F深度学习论文、代码库和资源链接，本身不是一个可独立运行的软件工具或框架，因此 README 中未包含具体的操作系统、硬件配置、Python 版本或依赖库安装要求。用户需根据列表中引用的具体子项目或论文复现代码来确定相应的运行环境。",[],[14],[93,94,95,96,97,98,99,100,101,102,103,104,105],"deep-trading","deep-learning","trading-algorithms","trading-bot","quantitative-trading","fintech","stock-trading","trading-bots","machine-learning","frequency-trading","deep-reinforcement-learning","deep-neural-networks","cryptocurrency","2026-03-27T02:49:30.150509","2026-04-20T04:06:36.276363",[],[]]