Share these talks and lectures with your colleagues
Invite colleaguesCase study
How to test AI: A case study of a machine learning-based trading system
Journal of Securities Operations & Custody,
17
(1),
26-42
(2024)
Abstract
The rapid evolution of artificial intelligence (AI) and especially machine learning (ML) has significantly transformed the technological landscape, influencing diverse sectors and making notable inroads into the realm of finance. This paper delves into the challenges posed by ML models, known for their black-box nature, non-deterministic behaviour, reliance on big data and inherent complexity, often lacking clear specifications. These characteristics present novel testing challenges compared to traditional software. In addressing these challenges, the authors introduce a conceptual framework tailored for testing ML-based systems, with a specific focus on financial applications. Theoretical concepts are exemplified through a real-world case study of the implementation of an ML-based bond trading system within a banking context. As the AI technologies become increasingly integrated into critical financial systems, a deeper understanding of their testing strategies will be essential for mitigating risks and harnessing their full potential. The heightened significance of in-depth testing knowledge, propelled by AI-driven progress, holds relevance for both testers and managers in navigating the complexities of the technological changes.
Keywords: artificial intelligence (AI); machine learning (ML); digital banking; innovation; testing; software testing; software quality; test automation
The full article is available to subscribers to the journal.
Author's Biography
Olga Lewandowska enjoys agile working at the nexus of business and IT, especially in the area of automation of the trading, clearing and settlement processes. Since 2007 Olga has been working as a consultant for customers such as Deutsche Bank, Deutsche Börse and other banks and clearing houses. Her recent interests encompass the application of big data and artificial intelligence (AI), especially machine learning (ML), in trade processing. Olga studied economics at the Warsaw School of Economics and at the Johannes Gutenberg University Mainz, Germany, majoring in investment banking. At the Johann Wolfgang Goethe University in Frankfurt she successfully completed her dissertation titled ‘Post-Trade Processing of OTC Derivatives – IT Solutions under a New Regulatory Paradigm’. Her research interests include securities trading, clearing and settlement; over-the-counter (OTC) and on-exchange traded derivatives; regulatory changes and their impact on IT systems; industrial organisation of financial markets; systemic risk in the financial system; AI/ML in finance.
Edgar Mai is a financial markets expert with a proven track record of helping financial companies designing robust IT trading solutions. Prior to his current role as Chief Executive Officer (CEO) of Mainstay, he was a manager at KPMG Financial Services. With more than 20 years’ consulting experience, Edgar has worked on several valuable projects, including the migration of the German security trading market Xetra to the new T7 trading platform of the Deutsche Börse. He holds a Master’s degree in economics from the Johann Wolfgang Goethe University in Frankfurt, Germany.
