Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Quant Science Profile picture
Quant Science
@quantscience_
Develop profitable trading strategies, build a systematic trading process, and trade your ideas with Python—even if you’ve never done it before.
12 subscribers
Sep 7 • 11 tweets • 4 min read
David Tepper has generated average annual returns of 28% since 1993.

But with Python, you can do it too.

This is how to make a David Tepper algorithm with Python: 🧵 Image Here’s a “Tepper-inspired” macro risk-on / risk-off allocator in Python.

It leans on public, high-level principles often associated with David Tepper’s approach (credit spreads, macro regime, volatility)
Sep 6 • 8 tweets • 3 min read
🚨BREAKING: A new open-source multi-agent LLM trading framework in Python

It's called TradingAgents.

Here's what it does (and how to get it for FREE): 🧵 Image 1. What is TradingAgents

TradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world hedge funds.
Sep 5 • 8 tweets • 3 min read
Can AI trade?

Introducing FinSphere: A real-time stock analysis agent

A 16-page PDF: Image 1. The Problem

The paper posits that LLMs struggle with 2 limitations:

1) Absence of evaluation metrics

2) Lack of stock analysis logic
Sep 3 • 4 tweets • 2 min read
Nothing beats the feeling of executing dozens of trades from Python via API.

All you need is:
1. Python
2. Interactive Brokers

Want to learn how? Image 🚨 LIVE Python Algo Trading Workshop: Learn how we built our hedge fund

• QSConnect: Build your quant research database
• QSResearch: Research and run machine learning strategies
• Omega: Automate trade execution with Python

👉 Get the system: learn.quantscience.io/become-a-pro-q…Image
Sep 2 • 17 tweets • 5 min read
12 Python libraries for free market data everyone should know: Image yfinance

Data for stocks (historic, intraday, fundamental), FX, crypto, and options. Uses Yahoo Finance so any data available through Yahoo is available through yfinance.

github.com/ranaroussi/yfi…
Sep 1 • 10 tweets • 4 min read
How to make a simple algorithmic trading strategy with a 472% return using Python.

A thread. 🧵 Image This strategy takes advantage of "flow effects", which is how certain points in time influence the value of an asset.

This strategy uses a simple temporal shift to determine when trades should exit relative to their entry for monthly boundary conditions. Image
Aug 31 • 4 tweets • 2 min read
The 5 things you need to start algo trading:

1. One trading strategy
2. A $500 computer
3. A broker with an API
4. An internet connection
5. The Python Quant Scientist Stack

That's it.

Want to learn how? Image 🚨 LIVE Python Algo Trading Workshop: Learn how we built our hedge fund

• QSConnect: Build your quant research database
• QSResearch: Research and run machine learning strategies
• Omega: Automate trade execution with Python

👉 Get the system: learn.quantscience.io/become-a-pro-q…Image
Aug 30 • 13 tweets • 4 min read
Stock Prediction AI: Using Machine Learning and Deep Learning to predict stock price movements in Python.

The Python code is 100% free on GitHub.

Let's dive in (bookmark this): Image 1. The Python Machine Learning and Deep Learning Libraries:

- mxnet
- gluon
- sklearn
- xgboost Image
Aug 28 • 5 tweets • 2 min read
JP Morgan's Python training.

Available 100% for free: Image Here's the link on GitHub: github.com/jpmorganchase/…Image
Aug 27 • 9 tweets • 3 min read
A 23-page research paper reveals the number 1 method Hedge Funds use to beat the market:

Time Series Momentum

This is how: 🧵 Image 1. What Is Time Series Momentum?

Time Series Momentum (TSMOM) bets on trends continuing. If a stock’s up, buy more; if down, sell. A 2011 study of 58 assets proved it works! Image
Aug 27 • 10 tweets • 4 min read
🚨BREAKING: A new Python library for algorithmic trading.

Introducing TensorTrade: An open-source Python framework for trading using Reinforcement Learning (AI) Image TensorTrade is an open source Python framework for building, training, evaluating, and deploying robust trading algorithms using reinforcement learning leveraging:

- numpy
- pandas
- gym
- keras
- tensorflow
Aug 26 • 8 tweets • 3 min read
🚨BREAKING: New Python Library for Algorithmic Trading with AI

It's called limex ziplime.

This is what you need to know: Image 1. What is ZipLime?

ZipLime is your AI quant for creating and backtesting trading strategies.

If you have an idea for a strategy or portfolio, just describe it, and I’ll help translate it into working code, run the backtest, and analyze the results.
Aug 17 • 8 tweets • 3 min read
The secret of hedge funds is revealed in a 41-page PDF:

This paper analyzed 464 stocks that 10X-ed over a 24-year period.

Here are the best factors that drive outperformance: (number 3 is the best 🧵) Image 1. Size Effect

"Small-cap stocks outperform medium and large companies in 11 out of 12 cases"

Smaller stocks tend to perform better, but it's not the only contributor. Image
Aug 15 • 5 tweets • 2 min read
JP Morgan's Python training.

Available 100% for free: Image Here's the link on GitHub: github.com/jpmorganchase/…Image
Aug 11 • 8 tweets • 3 min read
🚨BREAKING: Introducing QF-Lib

A new Python library for Quant Finance.

Here's everything you need to know... (a thread) 🧵 Image 1. What Is QF-Lib?

QF-Lib is a modular Python library that provides an advanced event-driven backtester and a set of high-quality tools for quantitative finance.
Aug 10 • 21 tweets • 4 min read
Look at this guy:

• Averaged 25% annual returns over 30 years
• Secret Sauce: Discounted Cash Flow

Here's how to trade just like him with algorithms in Python: Image His name is David Tepper.

David Tepper climbed from a modest Pittsburgh upbringing to Wall Street legend status, delivering ~25% annual returns over 30 years.

Let's unpack his strategy and standout trades:
Aug 9 • 9 tweets • 3 min read
A 23-page research paper reveals the number 1 method Hedge Funds use to beat the market:

Time Series Momentum

This is how: 🧵 Image 1. What Is Time Series Momentum?

Time Series Momentum (TSMOM) bets on trends continuing. If a stock’s up, buy more; if down, sell. A 2011 study of 58 assets proved it works! Image
Aug 8 • 14 tweets • 4 min read
Look at this guy.

He achieved zero losing years over 3 decades.

He delivered over 30% yearly returns by defying conventional wisdom.

Discover 7 key strategies that cemented his iconic status:
(No. 7 is sheer genius) 🧵 Image This is Stanley Drukenmiller:

• Made $1B shorting the pound
• 30% CAGR over 30 years
• 0 losing years

Here's the Drukenmiller algorithm: Image
Aug 4 • 9 tweets • 3 min read
Stock Prediction AI: Using Machine Learning and Deep Learning to predict stock price movements in Python.

The Python code is 100% free on GitHub.

Let's dive in (bookmark this): Image 1. The Python Machine Learning and Deep Learning Libraries:

- mxnet
- gluon
- sklearn
- xgboost Image
Aug 2 • 4 tweets • 2 min read
7 small steps to start with algorithmic trading:

1. Start with Python
2. Learn to use VSCode
3. Take a pandas tutorial
4. Then a plotly tutorial
5. Make a portfolio with riskfolio
6. Make a backtest with vectorbt
7. Analyze performance with vectorbt

You can do this! Image 🚨 Python Algo Trading Workshop on Thursday: Learn how we built our hedge fund

• QSConnect: Build your quant research database
• QSResearch: Research and run machine learning strategies
• Omega: Automate trade execution with Python

👉 Get the system: learn.quantscience.io/become-a-pro-q…Image
Jul 29 • 9 tweets • 4 min read
The secret of hedge funds is revealed in a 41-page PDF:

This paper analyzed 464 stocks that 10X-ed over a 24-year period.

Here are the best factors that drive outperformance: (number 3 is the best 🧵) Image 1. Size Effect

"Small-cap stocks outperform medium and large companies in 11 out of 12 cases"

Smaller stocks tend to perform better, but it's not the only contributor. Image