Quantitative investing seems mystifying to many–so much so that observers often refer to the investment process itself as a “black box.” Moreover, quantitative investing continues to grow in complexity, and today Two Sigma and others often employ powerful deep learning techniques in various parts of the process to make decisions informed by vast pools of data.
Even so, the process isn’t necessarily as mysterious as it’s sometimes made out to be. Two Sigma’s David Kriegman–who’s also a professor of computer science and engineering at the University of California San Diego–recently hosted a webinar to shed light on how Two Sigma researchers apply deep learning to sequences in quantitative investing.
As Kriegman explains, 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.
Curious how deep learning fits into the quantitative investment process? Watch the webinar here: