Python, from scratch, for professional quants. Nothing you don't need, everything you do.
Time to use Python the way real quants use it
"Learning Python" <> "Using Python to Make Real Trading Strategies"
Take a practical pathway to using Python speifically for quant finance and algorithmic trading – without all the generic content. Dr Tom Starke will guide you step by step (using Google Colab notebooks he will share) so you can get to actual strategy development outcomes fast.
Get competent with the real tooling (data handling, back-testing, libraries such as Pandas, finding alphas, performance & risk analysis, & so much more) so you can research faster, set up a full systematic trading stack or even improve your job prospects. Tom has the exact experience set to take you on this journey.
Yes, it would help if you had some very basic Python knowledge, but it’s not necessary, especially when AI can help answer questions along the way. Speaking of which, here’s a Custom GPT we created designed to help tutor you specifically in ‘Python for Quants’:
Welcome to the Institutional Quant Series
1. Introduction to Back-Testing in Python
THIS COURSE IS FREE FOR ALGO COLLECTIVE MEMBERS!!
From downloading data, constructing your first back-test to assessing your strategy.
2. Python Essentials for Quant Trading
Pandas, looping & vectorized back-tests, parameter sweeps, robustness testing, metrics & more.
3. Advanced Back-Testing in Python
From data prep & visualisation & constructing trading strategies to optimization.
4. The Complete Algo Trading Masterclass
From start to finish, 12 modules of training over all the aspects of Python used for developing strategies & trading like a pro.
Get Started Free
Join Algo Collective
Algo Collective members get the first course FREE. You’ll be able to work out if this is right for you, and engage with other professional traders in the community.
From within the Collective you’ll also be able to preview the content of the remaining courses.
Collaborate with Others
Even if you’re not in the Collective, each course contains its own community area where you can work through things with like minded learners.
Compound your efforts with teamwork.
Colab Notebooks & Quizes are included.
Four Distinct Courses
Course 01: Intro to Back-Testing in Python
Overview
Modules
Course 02: Python Essentials for Quant Trading
Overview
— Installing Python
Getting Financial Data
— Downloading Data Using APIs
— Reading Data From Files
— Working with Data Files
— Quiz
Data Preparation and Visualisation
— Building VWAP from a Text File
— Pandas for Financial Data
— Plotting Time Series Data
— Quiz
Building Blocks for Financial Analysis
— Handling Date and Time
— Converting Time Zones
— Calculating Returns
— Calculating Volatility
— Correlation in the Market
— Linear Regression Analysis
— Quiz
The Python Information Superhighway
— Data Structures
— Functions
— More Functions
— Map and Lambda
— Powerful Loops
— Quiz
Building a Trading Strategy
— Fundamentals of Trading Strategies
— A Simple Backtest
— Cointegration
— Formulating a Pairs Trading Strategy
— Constructing the Pairs Trading Backtest
— Strategy Analysis 1
— Strategy Analysis 2
— Quiz
Conclusion
— Final Remarks
Bonus Section
— Dealing with NaNs in Financial Time Series
— Parameter optimisation 1
— Parameter optimisation 2
Course 03: Advanced Back-Testing in Python
Overview
Preparing Financial Data for Back-Testing
— Resampling for Different Data Frequencies
— Filling Financial Data
Different Types of Back-Tests
— Pandas Back-test
— Looping Back-test
— Vectorised Back-test
Parameter Sweeps to Gain Insights
— An Example: Sweeping Different MA Windows
— Defining a Metric
— Visualisation: 3D Plots
— Visualisation: Contour Plots
— Robustness Testing
— Parameter Selection
Fundamentals of Portfolio Optimization
— Varying Asset Weightings
— Randomising Asset Weightings
— Finding the Best Asset Weightings
— Evaluating Performance of the Optimised Portfolio
Advanced Analysis
— Sortino Ratio
— CAGR (Compound Annual Growth Rate)
— Beta
— Monte Carlo Simulation
— Distribution of Returns
— Assessing the Strategy Further - Trimming the Tails
Exercizes
Course 04: Algo Trading Master Class in Python
Overview
— Installing & Importing Important Packages
— Downloading Stock Data & understanding Dataframes
— Visualizing Price Data
— Importance of Proper Python Indexing
— First Trading Strategy & Loops
Section 2
— Improving Trading Strategies
— Thresholds & Percentage Changes
— Plotting Profit Curves
— Cumulative Sum Vs Cumulative Product
— Graph Improvements & Dates
Section 3
— Data Snooping Pitfall
— Moving Average Crossover
— Mean Reversion Moving Average Crossover Strategy
— Trend Following Vs Mean Reversion Strategies
— Trend Following Short Trading
— Improving Trend Following Strategies
— Skewed Return Profile of Equities
— Realized Vs Unrealized Returns
Section 4
— Unrealized Returns & Dates
— Plotting Unrealized Returns
— Strategy Analysis
— Benchmark Comparison
— Risk Adjusted Returns
— Benchmark Calculations
— Dataframes & Drawdowns
— Profit Per Trade
— Quantstats Ratios
— Quantstats Plots
— Strategy Optimisation
— Uncorrelated Strategies
Section 5
— Correlation Coefficient
— Heatmap Analysis
— Vectorization & Signal Creation
— Relationship between Signals & Prices
— Speed Testing Strategies
— Effective & Efficient Research
— Brownian Motion Random Walk
— Geometric Vs Arithmetic Random Walk
— The Impact of a Positive Edge
Section 6
— Generating Price Data
— Scaling to 100,000 Trajectories
— Increasing to 500 Timesteps
— Monte-Carlo Simulation
— Non-Normal Distribution of Stocks
— Drawing Stock Return Distributions
— Reinvesting Vs Not Reinvesting
— Autocorrelation Types of Timeseries
Section 7
— Linear Regression
— Linspace & Polyfit Vs Polyval
— Correlation Coefficient & Covariance Matrix
— Positive & Negative Autocorrelation
— Resampling Function
— Mathematical Basis for Position Sizing
— Biased Coin Toss
— Fractional Investing
— The Optimal Percentage
— Margin of Error
Section 8
— Statsmodels ACF & PACF
— Lists Vs Arrays
— Optimal Betting Fraction
— Introducing Leverage
— Sharpe Ratio & Leverage
— The Kelly Formula
Section 9
— Multi Asset Trading Imports
— Aligning Assets
— Logarithmic Returns
— Cumulative Sum
— Combining Sharpe Ratios
— Weighting Strategies
Section 10
— Portfolio Optimisation with SciPy: Maximising Sharpe Ratio
— Maximising Sharpe with SciPy: Building the Objective Function
— QuantStats Reporting + Constrained Optimisation
Section 11
— Diversification 101: Building an Equal-Weight Portfolio (Row-Wise Means)
— Brute-Force Two-Asset Optimisation: Sweeping Weights, Fixing Vector Math
— Efficient Portfolio Optimisation with SciPy Minimize
— Debugging Portfolio Optimisation
— Adding a Third Asset + Plotting the Optimized Portfolio
— Portfolio Optimization Constraints
— In-Sample vs Out-of-Sample Testing for Portfolio Weights
Section 12
— Long-Short Portfolios: Using Negative Weights Correctly
— Cash-Neutral Portfolios: When Weights Sum to Zero
— Why “Sum of Weights = 0” Can Break Optimizers + Leverage Intuition
— Shorting Reality Check: Margin, Costs, and Why Equities Are Harder
— Predictive Modeling: Building an “Alpha” Factor
— Factor Testing: Correlation With Future Returns (Shift Matters)
— Parameter Tuning + Correlation Across Assets
— Rank Correlation: Detecting Non-Linear (But Monotonic) Relationships
— Spearman Rank Correlation in Python + P-Values
— Finding Real Signal: Spearman on Factors + Combining Uncorrelated Factors
Meet your mentor, portfolio manager
Dr Thomas Starke
Systematic trading researcher specialising in portfolio construction and diversified quantitative strategies.
“Quantitative trading is applied scientific research – my goal is to help traders turn ideas into robust, diversified strategies that survive real markets.”
Follow Tom on Substack & watch his podcasts on The Algorithmic Advantage here & here.
Dr Thomas Starke is a quantitative trader and portfolio manager with over 15 years of experience in systematic trading and quantitative research. His work focuses on the development of highly diversified portfolios built from multiple uncorrelated systematic trading strategies.
He is the founder of AAAQuants, a consultancy specialising in quantitative trading research, strategy development, and education. Through AAAQuants, Dr Starke has collaborated with hedge funds and proprietary trading firms on numerous systematic trading and portfolio construction projects.
Dr Starke has had a remarkable career spanning work at the proprietary trading firm Vivienne Court, leading strategic research projects for Rolls-Royce, co-founding a microchip design company and he currently trades for a leading quantitative trading firm in Sydney.
He holds a PhD in Physics from the University of Nottingham (UK) and has held academic positions as a senior research fellow and lecturer at Oxford University. Dr Starke has a strong interest in emerging technologies including artificial intelligence, machine learning, and quantitative computing methods. Alongside his professional trading work, he regularly teaches quantitative trading and enjoys sharing practical systematic trading approaches with students and researchers.
The Outcome: Full Control of Your Trading & Research Stack
If you want to take courses with practical outcomes for traders, whether for yourself or your firm, these courses are lazer focussed on the skills you need.
Even within the realm of using Python for trading, few have the deep skill and expertise to guide you with ‘what really works’, based on their many years of actual experience generating strategies for the world’s top trading firms.
Rather than wasting time with Python you won’t use, Tom skips the fluff and jumps straight into the tools, hacks and methods that really matter.
Here’s the Investment Opportunity
01. Introduction to Back-Testing in Python
Courses 2, 3 & 4: Three Course Bundle - SAVE 10%
02. Python Essentials for Quant Trading
03. Advanced Back-Testing in Python
04. A Complete Algo Trading Master Class in Python
Frequently Asked Questions
How much time do I need each week?
Entirely up to you! The courses are self-poaced.
Do I need to be able to code?
No. However, a general experience with basic coding principles is assumed, and ideally some extremely basic Python. If you don’t have these, don’t worry, AI can help answer questions along the way. See the Custom GPT we created for this purpose above!
How do I run Python?
You can simply use the Google Colab files provided to run with zero setup or cost on Google Colab. For an introduction to Colab, check this out:
What support do I get if I’m stuck?
These courses are priced for minimal support, but there is definitely a community area where you can collaborate with others and ask questions that we’ll do our best to answer.
Is there a community, and what’s it for?
Yes. It’s there for accountability, idea cross-checking, troubleshooting, and staying sane in a market designed to hijack your emotions. Most traders fail in isolation; community compresses the learning curve and reduces unforced errors. Joining the Collective is extra, but well worth it for deeper interactions with experts.
Do I already need substantial quant experience?
No. Experience helps, but the course introduces core testing concepts, definitions of key quantitative metrics, and foundational material so students new to quant analysis can fully benefit.
How does the guarantee work?
Let us know before you finish the course, within 14 days, and we’ll give you a full refund if you don’t think the course is meeting your objectives. No questions asked.