How People use AI in Finance

Songqi Zou
7 min readApr 12, 2020
AI for Quant

There are millions of trade made in the global financial market every day. Data grow very quickly and people are hard to understand. With the power of the latest artificial intelligence research, people analyze & trade automatically and intelligently. This list with research, code & tools where people try to beat the market.

Hello, billionaires of the future!

Papers

Courses & Book

Strategies & Research

Time series Process

Price and Volume process with Technology Analysis Indices

  • 🌟🌟 stockpredictionai: In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator.
  • 🌟 Personae: 📈 Personae is a repo of implements and environment of Deep Reinforcement Learning & Supervised Learning for Quantitative Trading.
  • AutomatedStockTrading-DeepQ-Learning: Every day, millions of traders around the world are trying to make money by trading stocks. These days, physical traders are also being replaced by automated trading robots. Algorithmic trading market has experienced significant growth rate and large number of firms are using it. I have tried to build a Deep Q-learning reinforcement agent model …
  • tf_deep_rl_trader: Trading Environment(OpenAI Gym) + PPO(TensorForce)
  • trading-gym: This trading-gym is the first trading for agent to train with episode of short term trading itself.
  • trading-rl: Deep Reinforcement Learning for Financial Trading using Price Trailing @ ICASSP 2019
  • deep_rl_trader: Trading Environment(OpenAI Gym) + DDQN (Keras-RL)
  • 🌟 https://github.com/wangshub/RL-Stock: 如何用深度强化学习自动炒股
  • Quantitative-Trading: 💸 Papers and Code Implements for Quantitative-Trading
  • gym-trading: Environment for reinforcement-learning algorithmic trading models
  • zenbrain: A framework for machine-learning bots
  • DeepLearningNotes: Machine Learning in Quant analysis

Portfolio Management

  • Deep-Reinforcement-Stock-Trading: A light-weight deep reinforcement learning framework for portfolio management. This project explores the possibility of applying deep reinforcement learning algorithms to stock trading in a highly modular and scalable framework.
  • qtrader: Reinforcement Learning for Portfolio Management
  • PGPortfolio: PGPortfolio: Policy Gradient Portfolio, the source code of “A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem

High Frequency Trading

Event Drive

  • 🌟🌟 stockpredictionai: In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator.
  • 🌟 trump2cash: A stock trading bot powered by Trump tweets http://trump2cash.biz

Crypto Currencies

TA

Lottery & Gamble

Arbitrage

  • ArbitrageBot: Arbitrage bot that currently works on bittrex & poloniex
  • r2: R2 Bitcoin Arbitrager is an automatic arbitrage trading system powered by Node.js + TypeScript.
  • cryptocurrency-arbitrage: A cryptocurrency arbitrage opportunity calculator. Over 800 currencies and 50 markets. https://cryptoworks.co
  • bitcoin-arbitrage: Bitcoin arbitrage — opportunity detector
  • blackbird: Blackbird Bitcoin Arbitrage: a long/short market-neutral strategy

Data Sources

Traditional Markets

  • 🌟 Quandl: Get millions of financial and economic datasets from hundreds of publishers via a single free API.
  • yahoo-finance: Python module to get stock data from Yahoo! Finance
  • Tushare: TuShare is a utility for crawling historical data of China stocks

Crypto Currencies

  • CryptoInscriber: 📈 A live cryptocurrency historical trade data blotter. Download live historical trade data from any cryptoexchange, be it for machine learning, backtesting/visualizing trading strategies or for Quantopian/Zipline.
  • Gekko-Datasets: Gekko Trading Bot dataset dumps. Ready to use and download history files in SQLite format.

Research Tools

Trading System

For Back Test & Live trading

Traditional Market

[System]

[Combine & Rebuild]

Crypto Currencies

  • [deprecated]Gekko: A bitcoin trading bot written in node —
  • zenbot: Zenbot is a command-line cryptocurrency trading bot using Node.js and MongoDB.
  • bot18: Bot18 is a high-frequency cryptocurrency trading bot developed by Zenbot creator @carlos8f https://bot18.net/
  • magic8bot: Magic8bot is a cryptocurrency trading bot using Node.js and MongoDB.
  • catalyst: An Algorithmic Trading Library for Crypto-Assets in Python http://enigma.co
  • QuantResearchDev: Quant Research dev & Traders open source project [BUILDING]
  • MACD: Zenbot Macd Auto-Trader
  • abu: A quant trading system base on python.http://www.abuquant.com/

Plugins

TA (Technical Analysis) Lib

  • pandas_talib: A Python Pandas implementation of technical analysis indicators
  • finta: Common financial technical indicators implemented in Python-Pandas (70+ indicators).
  • tulipnode: Tulip Node is the official node.js wrapper for Tulip Indicators. It provides over 100 technical analysis overlay and indicator functions. https://tulipindicators.org
  • techan.js: A visual, technical analysis and charting (Candlestick, OHLC, indicators) library built on D3. http://techanjs.org/

Exchange API

Do it in real world!

  • IbPy: Python API for the Interactive Brokers on-line trading system
  • HuobiFeeder: Connect HUOBIPRO exchange, get market/historical data for ABAT trading platform backtest/analysis and live trading
  • ctpwrapper: Shanghai future exchange CTP api

Framework

Visualizing

GYM Environment

  • 🌟 TradingGym: Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.
  • TradzQAI: Trading environnement for RL agents, backtesting and training.
  • btgym: Scalable, event-driven, deep-learning-friendly backtesting library https://kismuz.github.io/btgym/

Articles

Others

Other Resource

--

--