Sorry, you need to enable JavaScript to visit this website.

Machine Learning in Systematic Futures Allocation: A Model Comparison using Price-Based Features

Speaker: Tony Guida

How to book

Already a member? – Log in and book your free ticket 
Not a member yet? – Become a Basic Member for free here. You will then be able to claim your free ticket. 

Event Agenda 

17:30 - 18:30 GMT - CQF Institute Global Talk: Tony Guida

This event can earn you up to 2 CPD credits.

Abstract

Over the last seven years, Machine Learning applications in Finance have benefited from an increasing corpus of research stemming from academia and gradual adoption from practitioners in the investment industry. More recently, Systematic Trend Following strategies have been experiencing a tailwind in terms of realized performance and renew interest compared to other hedge funds strategies. In this educational presentation, we first review some general concepts about trends and how to build generic systematic trend following strategies according to classic definitions. Then we focus on the use of price-based features to construct a dataset designed for training different Machine Learning (ML) approaches (trees based and neural net based) to build diversified Futures portfolio. We finally conclude by contrasting the results between generic and ML based approach and how they relate to contemporary methodologies used in the systematic CTA/Trend following.

Speaker Bio

Tony Guida joined RAM AI in 2019 as a Senior Quantitative Researcher and became Co-Head of Systematic Macro. His work focuses primarily on extracting market inefficiencies from different sources from traditional fundamentals, market signals, alternative data and machine learning. Tony started his career at Unigestion in the Quantitative Equity Low Volatility Team and later became a member of the Research and Investment Committee In 2015, he moved to Edhec Risk Scientific Beta as a Senior Consultant for Risk allocation and Factor Strategies before going to a major UK pension fund in 2016 to build the in-house systematic equity, co-managing 8 billion GBP as a Senior Quantitative Portfolio Manager.

Tony is a Lecturer and researcher in Quantitative Finance and Machine Learning. He is the co-author and editor of 'Big Data and Machine Learning in Quantitative Investments and Machine Learning for Factor Investing' (R and Python versions).