Reinforcement Learning in Finance

We are onsite again!
And at such a nice location. We will have the ZKB atrium just for us.
Finance is all about time series, and reinforcement learning is AI for decision-making on time series, so how far can it bring us?
Let's get inspired and enjoy the famous ZKB apéro together.

To ensure you can access the ZKB building, please provide your full name here: https://forms.gle/gHZwSzDGxqhPcNh46

Agenda
18:30 Welcome
18:35 Alexander Posth & Christoph Auth: Introduction RL in Finance
18:45 Fernando De Meer Pardo & Florin Dascalu: Optimal Trade Execution with RL
19:15 David Jaggi & Linus Grob: Factor Investing with RL
19:35 Apéro riche (provided by ZKB)

Talks

Introduction RL in Finance
Although Reinforcement Learning (RL), one of the most promising research areas in Machine Learning, has demonstrated its immense potential for solving sophisticated real-world problems, it is still underused and understudied in financial applications.
"Strengthening Swiss Financial SMEs through Applicable Reinforcement Learning" is an Innosuisse Innovation project that aims to identify and address the challenges of applying RL in finance. By targeting and overcoming current RL implementation problems, this project will also help Swiss SMEs to gain a competitive edge.

Optimal Trade Execution with RL
The goal of optimal trade execution is to buy/sell a set number of shares of an asset in such a way that the price paid/received is optimal. The choice a trader or—nowadays better—an algorithm can make is how to slice the order over different smaller orders: this includes the number of shares for individual child orders, the time at which orders are placed, and the type of orders sent to an exchange. Optimal trade execution involves a sequential decision-making process and can therefore be represented as a Reinforcement Learning problem.

Factor Investing with RL
Factor investing is an investment approach that targets specific drivers of equity returns. These factors vary in strength during different market phases. We use reinforcement learning to automatically rotate the weighting of our portfolio between different return factors with the aim of achieving an investment return above the benchmark.

About the speakers

Dr. Jan-Alexander Posth is a senior lecturer at the Institute for Wealth and Asset Management at the ZHAW School of Management and Law, with a research focus GreenTech and AI in finance. He has more than 12 years’ of professional track record in the financial industry, where he gained extensive expertise as a risk manager, quant and portfolio manager.
Starting at Deutsche Postbank as a credit risk manager, Alexander moved on to Landesbank Baden-Württemberg where he led the fund derivatives trading desk. Joining STOXX Ltd. in 2012, he was responsible for the development of smart-beta equity indices before becoming Head of Research and Portfolio Management at a start-up hedge fund in 2015.
Alexander started at ZHAW in 2017; he holds a PhD in theoretical physics.

Christoph Auth is a senior scientific employee at ZHAW. He has multiple years of experience as a Quantitative Analyst in the Wealth and Asset Management industry both in Zurich and London where he was mainly responsible for portfolio construction and the development of systematic trading strategies. He holds an MSc in Financial Mathematics from Warwick Business School, UK.

Fernando De Meer Pardo is a PhD student who specialized in Deep Generative Models during his MSc studies. After working at the Industry for a couple of years, he has joined ZHAW for his PhD and is currently working on applications of Generative Models to Financial settings.

Florin Dascalu is a Research Assistant and a MSc student of Banking and Finance (Capital Markets & Data Science) at ZHAW. Previously, he worked as a Java software developer in the Market Risk team at UniCredit Bank. His interests include systematic strategies, signal processing, NN synthetic data generators, machine learning, and software development.

David Jaggi is a research associate at ZHAW School of Management and Law. Before joining ZHAW, David was a Data Scientist at Credit Suisse's Trade and Behavioral Analytics Team. He holds an MSc in Investments and Finance from Queen Mary University of London and a BSc in Engineering and Management. Currently, he is doing his PhD at the University of Zurich under the supervision of Markus Leippold. His main research interests involve Artificial Intelligence and Machine Learning with applications in finance.

Organizers
Claus Horn (ZHAW), Mark Rowan (Rowan Cognitive), Georg Russ (die Mobiliar)

Location
Zürcher Kantonalbank, Bahnhofstrasse 9, Atrium

Or you can join us online here!