💬 “The tone at the investment conferences over the last two years has changed from everybody being super excited to get access to new sources of data, to now, much more focused and critical questions. There’s more demand for demonstrations, people want proof there is value in the data before they purchase it.”
This is a conversation with Stefan Jansen
🎙️ Stefan is the founder and CEO of Applied AI. He advises Fortune 500 companies, investment firms, and startups across industries on data & AI strategy, building data science teams, and developing end-to-end machine learning solutions for a broad range of business problems.
Before his current venture, he was a partner and managing director at an international investment firm, where he built the predictive analytics and investment research practice. He was also a senior executive at a global fintech company with operations in 15 markets, advised Central Banks in emerging markets, and consulted for the World Bank.
He holds Master’s degrees in Computer Science from Georgia Tech and in Economics from Harvard and Free University Berlin, and a CFA Charter. He has worked in six languages across Europe, Asia, and the Americas and taught data science at Datacamp and General Assembly.
My co-host for this episode is Michael Berns, Michael is a Director at PwC where he leads the AI and FinTech Practice. He is an AI Thought Leader & FinTech Veteran, with 17 years of international experience on five continents.
🎧 In this episode, Stefan talked about the 2nd edition of his book Machine Learning for Algorithmic Trading: Predictive models to extract signals from market and alternative data for systematic trading strategies with Python.
There’s a significant amount of financial data to incorporate into machine learning models, and Stefan explained how to navigate this so that you can take action and makes decisions in the trading market. Stefan gives a retrospective view of what has changed with machine learning, freely available data, paywalled data and algorithmic trading over the last two decades.
The new edition of the book looks at modelling historical share prices developments over time to try out prediction models for future changes. Stefan told me that, beyond the trading models, finance generally attracts intellectually curious people, because it’s sophisticated, there’s math involved and when you add more varied datasets and computer science and machine learning to it, it takes this field of study to a whole new level.
For example he mentions new data sources such as satellite images that track how busy shopping malls are and the implications of this on retail and real estate share prices. This allows more creativity into this work too, he says. Innovation, technology and books like this from Stefan are enabling more democratic access to and use of information and this is enabling smaller investment shops to be more quantitatively driven. With his book, Stefan is not advocating for automated funds, but to help portfolio managers to be more data driven, systematic and create more sophisticated strategies.
Finally Stefan talks about the trends in data and how we’ve moved from a data land grab, to more sophisticated questions being asked and more proof of value being sought.