University of Cambridge > Talks.cam > Machine Learning @ CUED > Machine Learning for Quantitative Finance: A collaboration between the Cambridge Machine Learning Group and Cambridge Capital Management

Machine Learning for Quantitative Finance: A collaboration between the Cambridge Machine Learning Group and Cambridge Capital Management

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani.

We discuss some results from a collaboration between the Machine Learning Group and Cambridge Capital Management. We’ll briefly outline our attempts at using common trading signals to model (and predict) the returns from a portfolio of assets with some (relatively) modern machine learning techniques. Our focus will be on identifying the important characteristics of a model for asset returns, with a desire for rapid implementation on realistic amounts of data. We’ll see how some off-the-shelf implementations of popular methods, such as Gaussian processes, random forests, probabilistic linear models, and neural networks, perform on the prediction problem. We will also briefly look at the multi-step prediction problem and the use of these results for multi-step portfolio optimization. Along the way we’ll learn about some difficulties when working with training data, and why using machine learning in trading applications presents an interesting and difficult problem.

The talk will start with brief introductions from Zoubin Ghahramani (Cambridge) and Andrew Baxter (CCM), followed by presentations by Creighton Heaukulani and Matt Hoffman.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity