Mathematical Finance & Financial Data Science Seminar

Deep Reinforcement Learning for Asset Allocation in U.S. Equities

Speaker: Miquel Noguer i Alonso, Artificial Intelligence Finance Institute, NYU Courant

Location: Online

Date: Tuesday, April 13, 2021, 5:30 p.m.


Reinforcement learning is an area of machine learning that is concerned with maximizing the rewards in a given state, this makes it a very interesting area of research for the problem of portfolio management where the motive is to maximize the rewards in a given state of the market considering transaction costs.

While supervised and unsupervised agents solving the same problem face challenges in terms of transaction cost and risk management, a reinforcement learning agent has the end to end process built in while making a decision, making it the ideal machine learning based solution for the portfolio management problem.

We will show an application of deep reinforcement learning to create a financial model free solution to the portfolio management problem. We demonstrate this on a minute bar data for the top 25 stocks in the US equities universe. We define an explicit reward function. We use in our model several deep learning architectures:  Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory Networks (LSTM).

Speaker Bio

Miquel Noguer i Alonso is a financial markets practitioner with more than 20 years of experience in asset management, he is currently Head of Development at Global AI (Big Data Artificial Intelligence in Finance company) and Head of Innovation and Technology at IEF. 

He worked for UBS AG (Switzerland) as Executive Director. He is a member of European Investment Committee for the last 10 years. He worked as a Chief Investment Office and CIO for Andbank from 2000 to 2006. He started his career at KPMG. 

He is Adjunct Professor at Columbia University teaching Asset Allocation, Big Data in Finance and Fintech. He is also Professor at ESADE teaching Hedge Fund, Big Data in Finance and Fintech. He taught the first Fintech and Big Data course at the London Business School in 2017. 

He received an MBA and a Degree in business administration and economics in ESADE in 1993. In 2010 he earned a PhD in quantitative finance with a Summa Cum Laude distinction (UNED – Madrid Spain). He completed a Postdoc in Columbia Business School in 2012. He collaborated with the Mathematics department of Fribourg during his PhD. He also holds the Certified European Financial Analyst (CEFA) 2000. 

His research interests range from asset allocation, big data, machine learning to algorithmic trading and Fintech. His academic collaborations include a visiting scholarship in Columbia University in 2013 in the Finance and Economics Department, in Fribourg University in 2010 in the mathematics department, and giving presentations in Indiana University, ESADE and CAIA and several industry seminars like the Quant Summit USA 2017 and 2010.



This event is free, but requires registration.  Please click here to register.