This is a recurring event: View all events in the series “Data Bites”
Let’s get one thing out of the way fast: there’s no such thing as a market-predicting, magic AI box.
If there were, my employer would probably be called DataRobot Capital Partners and my colleagues and I would be running a hedge fund and drive expensive cars to our beachside villas, instead of selling software and professional services for a living.
But there's still plenty of value to be had from machine learning (especially the automated variety) in the financial markets. In this talk, I'll dig into some of the key topics when doing data science with financial time series:
- working with unstable signals
- the importance of metrics and baselines
- the joy of model factories
- the perils of target leakage, and
- avoiding overfitting on the problem statement.
About the Speaker:
Peter leads DataRobot’s financial markets data science practice and works closely with banking, financial services and asset management clients on their high-ROI use cases for DataRobot’s industry-leading automated machine learning platform.
He also contributes securities industry insights and thought leadership and is tasked with ensuring that DataRobot’s products meet the needs of the securities industry.
Peter joined DataRobot in 2018 and has twenty-five years’ experience in senior quantitative research, portfolio management, trading, risk management and data science roles. He completed City's M.Sc. Data Science programme in 2017.
Attendance at City events is subject to our terms and conditions.