An overview of best practices derived from building a machine-learning based starter bot for Halite, Two Sigma's public artificial intelligence programming challenge.
Entering 2018, it may be worth keeping an eye on “unconventional” risks, including monetary policy risk, political risk, and geopolitical risk. This article examines one way of measuring such risks and shows how they may interact with both equity prices and volatility.
With U.S. tax reform legislation seemingly poised for enactment, one might assume that policy uncertainty generally—and tax policy uncertainty, specifically—is falling. The reality is more complicated.
One way allocators can improve their inflation forecasts is to analyze it from as many perspectives as possible—just as a data scientist would.
A Two Sigma researcher introduces the Pandas UDFs feature in the upcoming Apache Spark 2.3 release, which substantially improves the performance and usability of user-defined functions (UDFs) in Python.
The authors provide a solution for the Efficient Server Audit Problem based on several new techniques, including simultaneous replay and efficient verification of concurrent executions, implemented for PHP web applications.
The cost of rolling futures contracts, rather than the decline in commodity prices, has been the largest drag on commodity index performance over the past 10 years. Although difficult to implement, asset allocators’ best response may be to develop dynamic execution strategies to mitigate the roll return “tax.”
A senior Two Sigma researcher provides an overview of some of the most interesting Deep Learning research from ICML 2017.
A group of Two Sigma statisticians highlight a selection of interesting talks and presentations from the 2017 Joint Statistical Meeting.
A Two Sigma engineer explains how the company implemented a high-availability networking architecture using OpenStack that's suitable for deployment at enterprise scale and beyond.