Department of Electronic and Computer Engineering Seminar - Creating Alpha with Machine Learning -- some examples
In this talk, we will present some of the Machine Learning techniques that are useful for medium frequency trading strategies, typically long/short market neutral equity portfolios.
We will start by explaining what the catch-all term “alpha” means in the context of systematic trading, and why some funds are specializing in harvesting this “alpha” for their clients. Then, we will present a couple of applications of machine learning tools (e.g., hierarchical clustering, PCA/MDS/t-SNE, Shapley values, graph neural networks, language models, Bayesian networks) which can help capture and preserve this elusive alpha.
Finally, we will conclude this talk with a high-level description of today’s quant trading landscape, and in which settings engineering and scientific minds are the most likely to shine.
Gautier Marti is a quantitative trader with experience in credit default swaps, corporate bonds, equities, and crypto futures markets. Currently working at ADIA in Abu Dhabi. Before joining ADIA, Gautier worked for hedge funds in Hong Kong, London, and Paris.
His research interests include (excluding proprietary research for alpha strategies) generative adversarial networks, knowledge graphs, graph neural networks, information geometry, geometry of correlation matrices, hierarchical clustering.