How to become a Quant Scientist:
Math:
• Calculus
• Linear algebra
Stats:
• Probability
• Time series analysis
Python:
• Pandas
• Zipline Reloaded
Markets:
• Economics
• Microstructure
#DataScience
meets
#Quant
#Finance
:
Can we use Anomaly detection to identify buy/sell patterns?
Anomaly detection for stocks in 4 steps.
A thread with
#Python
code 🧵
Python is truly remarkable for
#Quant
#Finance
.
This is the output of VectorBT - a new backtesting framework that is lightning fast.
If you want to learn more, here's our 7 step process 🧵
How to use anomaly detection for Algorithmic Trading in Python.
Just dropped our NEW article AND full code.
Plus it uses our NEW pytimetk package for anomaly detection.
Article:
#Quant
#Science
#DataScience
#Trading
Signal processing with Fast Fourier Transform is a powerful tool for financial analysis.
Here are 4 examples how you can use FFT in Quantitative Analysis. 🧵
Average True Range (ATR) is an essential technical indicator for volatility signals.
In 3 minutes, I'll teach you what took 3 months to learn.
Let's dive in. 🧵
#Quant
#Trading
#Algorithms
#Python
Machine learning steps for quant finance.
The most important part of creating a predictive investment strategy is setting up the data properly.
In this thread, I'll share 3 months of research on developing predictive ML models in finance.
A thread 🧵
🛑Myth: You need a $20,000/year license to Bloomberg Terminal to trade like a Hedge Fund.
✅Reality: Python and InteractiveBrokers (both are free)
Ready to build Algorithmic Trading Strategies (that actually work)?
👉Join us at our launch party here:
#Python
is insane for
#Quant
#Finance
.
I just stumbled across this treasure trove of 150+ quantitative finance programs in Python.
100% free.
T/Y
@pyquantnews
👉Link:
The Relative Strength Index (RSI) is a key indicator of overbought and oversold conditions.
In 2 minutes, I'll share 2 months of research on RSI.
Let's dive in. 🧵
#Quant
#Trading
#Algorithms
#AlgoTrading
Machine learning steps for quant finance.
The most important part of creating a predictive investment strategy is setting up the data properly.
In this thread, I'll share 3 months of research on developing predictive ML models in finance.
A thread 🧵
Filtering noise is the most challenging part of algorithmic trading.
Here are our 10 best filtering strategies.
Let's break each down. 🧵
#Quant
#Science
#Trading
#Algorithms
Myth:
AI bots are taking over the markets.
Truth:
Most shops still run Excel '97.
(But *some* shops are using machine learning)
Here are the 10 ways to use machine learning in trading (with the Python library):
How to use anomaly detection for Algorithmic Trading in Python.
Just dropped our NEW article AND full code.
Plus it uses our NEW pytimetk package for anomaly detection.
Article:
#Quant
#Science
#DataScience
#Trading
Rumor has it that Renaissance Technologies (RenTech) uses Fourier Transforms to extract signals from noisy stock data.
At 11AM EST today, we'll share how to do signal processing with Fourier Transforms in Python.
👉 Join here:
The
#python
ecosystem for algorithmic trading continues to get better. 🚀
Today we just added a new library to our Python Quant Stack (Dev Version):
skfolio: Scikit Learn meets Portfolio Optimization.
Let's dive in. 🧵
Python is crazy for finance and trading:
• 200,000+ powerful, pre-built packages
• Interactive Brokers integration
• Easy to learn for beginners
• Open source (FREE)
Want to learn how?
Join us on May 29th:
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):
Python is insane for algorithmic trading.
The ecosystem keeps getting better.
Case in point: vectorbt
This is simulating a buy-and-hold for BTC and ETH.
Trading is an unfair game.
Hedge funds and wall street elite have:
Better tools.
More information.
Automated execution.
That ends on Wednesday. This is what's coming.🧵
Awesome systematic trading.
A collection of the 97 best
#python
libraries for research and live trading.
696 strategies.
55 books.
23 videos.
All available right here (for free):
#AlgoTrading
#Quant
#Finance
The Average True Range (ATR) is a technical analysis indicator used to measure market volatility.
What can you do with ATR?
👉Find out in this free training:
#AlgoTrading
#Quant
#Python
FinR
The first open-source framework for financial reinforcement learning.
A library that develops a stock selection and trading strategy based on machine learning and AI algorithms.
Get it here:
🛑Myth: You need a $20,000/year license to Bloomberg Terminal to trade like a Hedge Fund.
✅Reality: Python and InteractiveBrokers (both are free)
Ready to build Algorithmic Trading Strategies (that actually work)?
👉Join us at our launch party here:
Free code from the book:
Algorithmic Trading with Python: Quantitative Methods and Strategy Development
Quant trading with:
• NumPy
• pandas
• Scikit-learn
Code included below:
Portfolio optimization with machine learning.
Sound complicated?
It is unless you have skfolio.
Advanced machine learning techniques in a few lines of Python:
The most liberating part of trading is executing orders with code.
This opens up so many opportunities. And it levels the playing field.
Let me explain. 🧵
Python is mind-boggling. Take this portfolio chart.
I made it in 15 lines of code.
And 3 python packages.
That's it. Want to learn how? Join us on July 31st:
Finance is feature engineering.
Algorithmic trading is just 1 step after prediction.
Want to learn how to get started with algorithmic trading?
👉Join us live May 29th:
Data scientists make better algorithmic traders than any other domain I know. According to Jim Simons, they have:
1. Data analysis
2. Technical acumen
3. Programming
This is why. 🧵
The secret to algorithmic trading?
Finding signal through the noise.
Learn about Signal Processing with the Fast Fourier Transform in Python.
Full Tutorial:
Building a Risk Parity portfolio used to be difficult.
Not anymore with Skfolio.
We kicked the tires on this new python package.
Get the tutorial and code here:
Why Python is amazing for finance (and algorithmic trading).
I just ripped through a simple factor analysis in under 50 lines of code.
It's made possible by alphalens.
And I'll teach you how on Sunday. (Join my newsletter here):
Python is insane for finance.
Factor investing analysis can be done in under 40 lines of code.
I'll show you how on Sunday in my QS Newsletter.
👉Join here:
You don't need a PhD to become an algorithmic trader. You need:
1. Python
2. One trading strategy
3. Interactive Brokers
That's it. Want to learn how? Join us on May 29th:
Skip the master's degree.
These 17 Python repos will teach you more about algorithmic trading than all your professors at school.
Without costing you $120,000:
20X faster than pandas.
Made for large-scale financial data engineering.
That's the story. 📚
I'll share what we are working on in our QS newsletter tomorrow.
👉Join here:
My framework for algorithmic trading:
1. Hypothesis formation: Generate ideas, collect data, analyze
2. Experiment setup: Backtest, test the backtest, iterate
3. Measure results: Risk and performance metrics
4. Execution: Paper trade, tandem trade, automate