A Bloomberg Terminal costs $30,000 per year.

Unaffordable for 99.9% of us.

But Bloomberg is not AI-enabled.

OpenBB dropped the $0 replacement with AI agent workspaces.

Free market data and an AI Copilot:

The 90-second step-by-step guide: In case you're unfamiliar:

OpenBB is the first AI financial terminal that combines data integration with an AI agent to transform investment research.

• Private (your data is not shared)
• 100s of free data sources
• Custom data backends
• Advanced AI Copilot

How it works:

Jupyter Notebook is the most powerful tool Python developers have.

But most people don’t know the hidden features.

Need a quick web app?

Or create REST APIs?

Here's the 6 ways to use Jupyter notebook you never knew existed: Jupyter Notebook is a web app for creating and sharing computational documents.

When I say powerful, here's what I mean:

• It supports 40 languages
• Produces rich, interactive output
• Leverages big data tools like Spark

So, what else can we do with Jupyter Notebook?

99% of beginners get backtesting wrong:

Build backtest, get poor results.

Tweak backtest, get positive results.

Then they wonder why they lose money.

Here's the dead-simple framework the pros use to get backtesting right: If you replicate this framework, you’ll:

• Setup a backtest with bt
• Run a backtest and analyze results
• Assess how random your results are

Plus, you’ll dramatically reduce the risk of your strategy performing poorly in the market after a great backtest.

But first…

I'm 43.

If you're still in your 20s or 30s, read this: 1. The compounding effect of doing the same thing over and over for a long period of time is a force of nature. Learn how to compound.

2. Learn how to be comfortable with being uncomfortable. Wealth doesn't accrue to people solving easy problems.

This is Edward Thorp.

The genius mathematician that returned 20%+ over 30 years.

He traded for 19 years, with his worst loss being 1%.

He beat Vegas dealers at blackjack.

His top 7 trading strategies (and how they work): 1. Statistical Arbitrage

He used mathematical models to identify price discrepancies between different markets or securities, buying undervalued assets and selling overvalued ones.

The best way to lose money with algo trading:

Overfitting to noise.

It’s how traders turn $100,000 accounts into $100.

So I spent 20 hours studying the state-of-the-art technique to learn how to keep my money.

Here’s the step-by-step guide to set it up (for any strategy): Algo trading is a game of iteration.

The faster you can test parameter combinations, the faster you can discard ones that don’t work.

And nothing is faster than vectorbt.

It’s a state-of-the-art library that runs millions of simulations in a few seconds.

Here’s how it works:

I spent $90,000 on a master's degree to learn math for finance.

These are the 16 most important stochastic processes for asset pricing (bookmark this thread for later): 1/16 Bessel Process

Models the radial part of a particle's path in motion.

Used to quantify risk in mean-reverting financial instruments.

Most algorithmic traders only focus on the trade signal.

Then they wonder why they lose money.

It's not the signal that's most important.

It's the filter.

Here are 9 of the most popular filters everyone should know (with Python code): Moving average filter

Uses a moving average of the data points to smooth out short-term fluctuations and highlight long-term trends.

It wasn’t until I met an old time options trader that I learned my mistake:

“I make money when others are panicking because they push the prices too far.”

I was trying to data mine strategies.

He was telling me to find inefficiencies.

That’s when everything changed: When I first started trading, I thought success meant find the perfect trading strategy.

I spent countless hours backtesting, optimizing, and data mining.

I thought I had found the holy grail of trading.

But when I traded my strategy live, I lost money.

Over and over again.

This is Steve Cohen.

He's America’s most profitable day trader and has a net worth of $19.8B

Here’s his story: Steve grew up in a middle-class family on Long Island with 7 siblings.

He liked sports.

Played basketball, soccer, and golf just like everyone else did.

He developed an obsession for poker, which eventually led him to trade.

Here’s how he got started:

Most investors struggle to find alpha.

So I spent 6 months reading everything I could

• Howard Marks (billionaire)
• Jim Simons (billionaire)
• Goerge Soros (billionairee)

Here's how the billionaires do it: 1. Cycles are inevitable:

Market cycles are an inherent part of the economic and investment landscape.

Recognizing this cyclical nature is crucial for investors.

I spent the last 25 years wasting my time writing 100,000 lines of code.

Most of the time, it was for analytics apps.

Now I can build 10 apps in under an hour.

All with Streamlit.

Here's the code: Streamlit lets you build beautiful web apps in a few lines of code.

This app downloads stock data and lets you apply technical analysis.

Want to get started with Python for quant finance?

Step 1:

Install your custom Python Quant Lab.

Start with these 14 (free) Python libraries: By the end of this thread, you'll have the right libraries for:

• Numerical libraries & data structures
• Financial instruments & pricing
• Backtesting & trading
• Market data

Let's go!

Free code from the book:

Hands-On Machine Learning for Algorithmic Trading

Get it here: 21 chapters of Python code.

All free:

github.com/PacktPublishin…

There are 580,000 Python libraries on PyPi.

But you only need 11 for quant finance: pandas

• Allows quick data cleaning and preprocessing
• Provides DataFrame structure for time-series data
• Enables complex data operations with simple syntax

Use it for:

Manipulating and transforming financial market data.

A Bloomberg Terminal costs $30,000 per year.

Last month, OpenBB dropped the $0 cost replacement.

Get 405 free data sources and an *AI Copilot*.

The 90-second step-by-step guide: In case you're unfamiliar:

OpenBB is the first AI financial terminal that combines data integration with an AI agent to transform investment research.

• Private (your data is not shared)
• 100s of free data sources
• Custom data backends
• Advanced AI Copilot

How it works:

The cost behind the Python Quant Stack:

• SciPy: $0
• Zipline: $0
• Python: $0
• NumPy: $0
• PyFolio: $0
• Pandas : $0
• OpenBB: $0
• Empyrical: $0
• AlphaLens: $0
• Statsmodels: $0
• RiskFolio-Lib: $0

Here's how to get started: Orientation

We'll start with the foundations. You'll learn how the course works, my expectations of you as a student, and how to make the most of your investment.

One way to get started with algorithmic trading:

Buying a $90,000 master's degree from MIT.

The other way:

YouTube.

The 10 YouTube videos to get you up and running today: Algorithmic Trading Using Python - Full Course

A comprehensive course on algorithmic trading using Python.

There are 137,000 Python libraries.

But you only need 11 for quant finance: pandas

• Allows quick data cleaning and preprocessing
• Provides DataFrame structure for time-series data
• Enables complex data operations with simple syntax

Use it for:

Manipulating and transforming financial market data.

OpenBB dropped the $0 cost Bloomberg replacement.

You can get 405 free data sources (and an AI Copilot).

Here's what you missed (in 90-seconds): In case you're unfamiliar:

OpenBB is the first AI financial terminal that combines data integration with an AI agent to transform investment research.

• Private (your data is not shared)
• 100s of free data sources
• Custom data backends
• Advanced AI Copilot

How it works:

Want to get started with Python for quant finance?

Step 1:

Install your custom Python Quant Lab.

Start with these 14 (free) Python libraries: By the end of this thread, you'll have the right libraries for:

• Numerical libraries & data structures
• Financial instruments & pricing
• Backtesting & trading
• Market data

Let's go!