Events and Talks 2025

Quantitative finance is a highly competitive field, leveraging statistical analysis to gain a small but repeatable edge in the markets. Throughout the decades, many innovative algorithms have come and gone – initially successful but eventually losing their power, as they become publicly known and widely traded. In a way, systematic funds are engaged in a never-ending arms race of turning publicly available information as quickly and as accurately as possible into a fair price, and efficiently acting on those opportunities that are currently over- or undervalued.

To maintain our edge GSA is exploring new markets, investing into increasingly faster trading models, and utilizing more available data. While this creates new opportunities, it also comes with new challenges requiring our technology to become more sophisticated, more autonomous, and more performant.

In this talk we will discuss how GSA is handling these challenges on a case study of one of GSA’s equity trading teams. We will explore both the technology and research side of our work on data and feature engineering, large scale ML research on in-house datacenters, and backtesting of trading models.

Julian completed his MSc. in Computer Science from Oxford in 2020. He then worked for Amazon Alexa where he researched Text-to-Speech machine learning models before joining GSA Capital in 2021. His time at GSA is spent researching feature engineering and selection, timeseries machine learning, and portfolio optimization.

Outside of work he enjoys rowing and plays the guitar.