024 – Trading Think Tank 02 – Battle of the Back-Testers
Aug 23, 2024
auto_awesome
Join Jason Strimpel, a quantitative risk manager and tech leader, and Marsten Parker, a legendary systematic trader, as they dive into the art of back-testing in trading strategies. They explore different tools like Python and Real Test, comparing their strengths and weaknesses. The conversation highlights the critical role of understanding the mechanics behind back-testing, and they share insights on learning Python for trading success. Their discussion also emphasizes the importance of robust workflows and sanity checks to enhance trading efficiency.
Understanding the fundamental mechanics of backtesting engines is essential for developing effective trading strategies and achieving accurate results.
The importance of user-driven development is emphasized, showcasing how feedback can refine backtesting engines like RealTest and PyQuant.
Data integrity is crucial in backtesting, as accurate historical data helps prevent biases like survivorship bias from skewing trading strategy performance.
Deep dives
Backtesting Fundamentals
Backtesting is a crucial process for traders, especially in systematic trading and algorithmic trading. Understanding the fundamental mechanics behind backtesting engines is vital for developing effective trading strategies. The panelists discuss different approaches to building backtesting engines, emphasizing the importance of knowing the underlying assumptions and how data is handled in the process. They share insights into the challenges of ensuring that trades mimic live trading conditions, highlighting that a successful backtest should align closely with expected real-world performance.
Building Custom Backtesting Engines
One of the key topics covered is the construction of custom backtesting engines using programming languages like Python. Jason Strymple highlights his experience in developing a backtesting engine called PyQuant, which is designed to assist traders in quantitative finance. Marston Parker shares his background in software engineering and discusses his RealTest engine, which has evolved through user feedback to meet the specific needs of traders. This highlights the significance of user-driven development in creating tools that truly serve the trading community.
Technical and Analytical Skills in Trading
The conversation reveals the importance of both technical skills and analytical thinking in the field of quantitative trading. Panelists stress that learning to code, particularly in Python, is essential for modern traders as it allows for greater flexibility and customization in developing and testing strategies. They discuss how there is a vast difference between merely operating software and understanding the code behind trading algorithms. This understanding enables traders to troubleshoot, optimize, and refine their strategies effectively.
The Challenge of Data Quality
Data integrity and quality are critical when backtesting trading strategies, as issues like survivorship bias can skew results. The panelists discuss various data sources, including Norgate Data, to ensure that traders have reliable and accurate historical data for testing. They emphasize the need to handle data thoughtfully to avoid introducing biases that can misrepresent the strategy's performance. Acknowledging the nuances of data handling and adjustments for splits and dividends is also vital for realistic backtest results.
Iterative Strategy Development
An iterative approach to developing trading strategies is highlighted as a key theme throughout the discussion. Panelists emphasize the need to continuously test and refine strategies based on historical performance and evolving market conditions. Using various backtesting frameworks allows traders to efficiently conduct multiple iterations, helping them identify viable strategies amidst a sea of possibilities. They stress the importance of not only recognizing statistical significance but also the need for practical robustness in strategy implementation.
In our second Trading Think Tank round table discussion we bring together two exceptional minds in the trading technology space to talk about building back-testing applications: in the blue corner representing Python - Jason Strimpel, an experienced quantitative risk manager, trader and technology leader, and in the red corner representing his own application (Real Test), Marsten Parker, a legendary systematic trader and bona fide Market Wizard. The discussion dives deep into the nuances of back-testing proficiently, highlighting the importance of understanding the underlying mechanisms in your chosen engine and the diverse approaches to creating robust trading strategies with the powerful tools we have on hand in the modern era.
Discounts on the Python for Finance course as well as links to the software and data providers are all on our site: www.thealgorithmicadvantage.com/tools
Get the Snipd podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share & Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode