Deep Learning for Sequences in Quantitative Finance
The quantitative investment process can be viewed as one that takes in raw data at one end and executes trades that buy and sell financial instruments at the other end. The process naturally decomposes into steps of feature extraction, forecasting the returns of individual instruments, portfolio allocation to decide quantities to trade, and trading execution. Many of the steps in this process are readily expressed as machine learning problems that can be addressed using deep learning sequence methods. This talk will provide an overview of this pipeline and deep learning for sequences. No background knowledge in finance or deep learning is required.
David Kriegman joined Two Sigma’s AI Core team in January 2021, and he is a Professor of Computer Science & Engineering at the University of California, San Diego. After receiving a BS EECS at Princeton and a PhD EE from Stanford, he joined the EE faculty at Yale and then the CS Department at the University of Illinois, Urbana-Champaign. Kriegman's core research is in computer vision and machine learning, and he has applied this to face recognition, robotics, coral ecology, medical imaging, microscopy, computer graphics, etc. His papers have been cited over 50,000 times, and he has received best paper awards at the three major computer vision conferences (CVPR, ECCV, and ICCV). He was the Editor-in-Chief of the IEEE Transactions on Pattern Recognition & Machine Intelligence, and he is a Fellow of the IEEE. Kriegman co-founded two companies, and KBVT, which developed face recognition technology, was acquired by Dropbox in 2014. Subsequently, he led the Machine Learning team at Dropbox.