Deep Latent Variable Models

In our previous article, we introduced latent variable models, where the latent variable can be thought of as a feature vector that has been “encoded” efficiently. This encoding turns the feature vector X into a context vector z. Latent variable models sound very GenAI-zy, but they descend from models that quant traders have long been […]
We’re Not Neutral on Market Neutral

Written By The QTS Team Continuing our series on foundational investing topics, we’re taking a closer look at something that’s been around for decades yet remains underused by many allocators: market-neutral investing. It’s a concept that’s simple in theory but deeply powerful in practice, especially when used as a building block in modern portfolios. Before […]
Feature Selection in the Age of Generative AI

Features are inputs to machine learning algorithms. Sometimes also called independent variables, covariates, or just X, they can be used for supervised or unsupervised learning, or for optimization. For example, at QTS, we use more than 100 of them as inputs to dynamically calibrate the allocation between our Tail Reaper strategy and E-mini S&P 500 […]
Stepping Back for a Better View

TL;DR The New Year invites reflection on the past and planning for the future. Recent geopolitical shifts mark the start of a new macroeconomic context for investment strategies, with two technologies already shifting the political and economic landscape. Change is inevitable and fortune favors the prepared. As we reflect on the past we prepare for […]
I’ll Have the Managed Futures, Please

TL;DR Broadly speaking there are two sources of investment returns available to investors – risk premia and alpha. Many investors concentrate their asset class risk premia and alpha exposure within equities. Managed futures can provide exposure to alternative, diversifying risk premia, as well as to a class of alpha strategies distinct in approach and correlation […]
Protecting your Portfolio from Crisis

You Insure Big Ticket Items, Why Not Your Portfolio? Most people choose to insure their largest and most valuable assets. Home insurance, car insurance, health insurance, boat insurance, the list of insurance policies goes on. As we consider the list of assets that people choose to insure, we discover a startling exception to the pattern […]
Applying Corrective AI to Daily Seasonal Forex Trading

By Sergei Belov, Ernest Chan, Nahid Jetha, and Akshay Nautiyal Abstract We applied Corrective AI (Chan, 2022) to a trading model that takes advantage of the intraday seasonality of forex returns. Breedon and Ranaldo (2012) observed that foreign currencies depreciate vs. the US dollar during their local working hours and appreciate during the local working […]
Metalabeling and the Duality Between Cross-Sectional and Time-Series Factors

By Ernest Chan and Akshay Nautiyal Features are inputs to supervised machine learning (ML) models. In traditional finance, they are typically called “factors”, and they are used in linear regression models to either explain or predict returns. In the former usage, the factors are contemporaneous with the target returns, while in the latter the factors […]
The Amazing Efficacy of Cluster-Based Feature Selection

One major impediment to widespread adoption of machine learning (ML) in investment management is their black-box nature: how would you explain to an investor why the machine makes a certain prediction? What’s the intuition behind a certain ML trading strategy? How would you explain a major drawdown? This lack of “interpretability” is not just a […]
Is News Sentiment Still Adding Alpha?

By Ernest Chan and Roger Hunter Nowadays it is nearly impossible to step into a quant trading conference without being bombarded with flyers from data vendors and panel discussions on news sentiment. Our team at QTS has made a vigorous effort in the past trying to extract value from such data, with indifferent results. But […]
