Michael Himmel is a Founding Partner, Portfolio Manager and Director of AI Research for Essex Asset Management.
He has been actively trading and designing systems since the 1980s, managing the No.1 Global Macro Hedge fund in the world in 1999.
He now uses large doses of AI and Machine Learning in his current practice.
In this week’s episode we discuss Artificial Intelligence, the challenges and applications of AI in trading, criticisms of Machine Learning, event studies and the importance of selecting datasets. He also shares insights from starting out as a runner for some of the biggest players in the 1980s, to managing the no. 1 global macro hedge fund in 1999 to using AI in his practise today.
Even if you’re not into AI and machine learning, the stories and insights Michael shares are invaluable.
- Lessons from running orders for some of the big players in the 1980s
- Transitioning from discretionary to systematic trading
- The challenges of applying Artificial Intelligence (AI) and Machine Learning in the 1990s
- How changes in technology have made AI in trading available to almost every body
- How Hedge Fund Lambeth Capital achieved a 260% return in 1999
- The impact September 2001 events had on hedge fund operations
- The applications of AI in non-finance industries
- The three divisions of AI
- The relationship between machine learning and AI
- Trading applications of AI
- How to decide which datasets should be used to avoid data mining
- Addressing the criticisms of machine learning
- The challenges of using AI for longer timeframes and is it the right tool for the job?
- Event studies in trading
- The future of trading
Show your support
While you’re listening, it would be great if you could show your support by leaving a brief review of the podcast in iTunes. This really helps to spread the word and reach even more listeners!
Resources mentioned in this episode
Top tips from this episode
Here are few of my favourite takeaways from the chat with Michael:
- Selection of datasets – Michael mentioned that the selection of datasets is critical. He has selected datasets which make logical sense, so even though he is allowing an algorithm to determine the weighting of the datasets he is making sure the computers are looking through datasets that make intuitive sense. These principals can be applied to trading styles outside of AI and machine learning too, does your model make sense, is it logical or have you just mined the data to find something that appears to work in the past but has very little chance to work in the future?
Got A Question, Topic or Guest you want to see on the Podcast?
Do you have a specific question, topic or guest you’d like to see on a future podcast episode?
Click here and submit your suggestion for a chance to have it featured on an upcoming podcast episode.
Get the Transcript
Subscribe to Better System Trader and never miss another episode!
Please support the podcast by giving an honest Rating/Review for the show on iTunes!