PAPER

Machine Learning Factors Capturing Non Linearities in Linear Factor Models 

Asset Allocation and Asset Liability Management , Factor and Risk Modeling , Investing (Investment Management) , Performance Analysis , Portfolio Construction and Optimization , Risk Management

BLOG

Is There a Hedge-Fund-Crowding Factor? 

Factor Investing

Hedge funds held heavy, relatively illiquid short positions in crowded stocks before the January 2021 short squeeze. We created a risk factor that added explanatory power and may provide insights into potential short squeezes and other risks.

BLOG

Are (Stock) Bubbles Rising? 

Factor Investing

How does one identify or quantify a bubble? We propose a framework for assessing the “bubbliness” of stocks and portfolios, rooted in the idea that bubbles are driven by the same forces, and share characteristics with crowded trades.

PAPER

The Many Faces of Sentiment 

Factor and Risk Modeling , Investing (Investment Management) , Performance Analysis , Portfolio Construction and Optimization , Risk Management

BLOG

Are Momentum’s Wings Finally Starting to Melt? 

Factor Investing , Factors

Positive vaccine news on Nov. 9 caused big moves in industry and style factors. Those hit hardest this year jumped, while previous high performers slumped. Did this mark new factors leadership and a long-awaited rotation from momentum to value?

PAPER

What Type of Companies Were Best Prepared for Remote Work? 

Factor and Risk Modeling , Performance Analysis , Portfolio Construction and Optimization , Risk Management , COVID-19

COVID-19 disrupted the operating models of many businesses and forced a shift to remote working, digitization and low-contact transactions and services, which we term “Remote Operation Capability” (ROC). Some corporations were better positioned to take advantage of a remote, automated and digitized operating environment. We utilized machine-learning and natural language-processing techniques to build a potential ROC factor that looks at the extent to which a company was more likely to thrive in such an environment. The techniques we present potentially could be leveraged to capture other emerging or long-term themes.

PAPER

Straight Talk on Nonlinearities in Linear Factor Models 

Factor and Risk Modeling , Investing (Investment Management) , Performance Analysis , Portfolio Construction and Optimization

Linear regression models have been the workhorses of finance and economics. However, given increasing attention to nonlinear methods, we investigate the extent to which nonlinearities not captured by standard linear models within equity factor risk models are present. Adding nonlinear factors in simple polynomial functions of their linear counterparts contributed some additional explanatory power to the cross-section of security returns. Furthermore, some generated factor returns and information ratios higher than corresponding linear factors. Overall, we found linear models created a robust framework to identify relationships between factor exposures and security returns through simple linear factors or transformed (e.g., polynomial) variants.

BLOG

Hunting a COVID-19 factor 

Factor Indexes , Factor Investing , Factors

Can we identify a COVID-19 factor and quantify companies’ exposure to it? We explored three ways to do so — from very simple to more complex methods.

PAPER

Looking for a better hedge 

Asset Allocation and Asset Liability Management , Factor and Risk Modeling , Investing (Investment Management) , Portfolio Construction and Optimization , Risk Management

Peer selection and understanding relationships between companies play a pivotal role in many areas of finance. Previously, we described a methodology for quantifying the similarity between every pair of companies from the text of their business descriptions in 10-K filings, fundamentals, news mentions and return correlations. We showed how the resulting similarity score matrix could be used to identify pairs or groups of similar companies (peers), which have numerous potential applications. Here we analyze ways to use this data for modeling simple hedging portfolios, minimum-volatility (min vol) portfolios and optimized hedging portfolios.

BLOG

The coronavirus market impact spreads globally 

Factor Investing , Global Investing

Fear of a coronavirus pandemic and ensuing economic impacts caused sharp drops in global markets after an initially mild response. We look at recent performance from a factor perspective and how quickly factor returns and volatility reverted in past crises.

BLOG

Factors separated fact from fiction 

Factor Indexes , Factor Investing , Factors

Technological advances have expanded the application of factors. What was the realm of quantitative investors has become more accessible, bringing greater transparency and potential insight into portfolio characteristics and performance drivers.

PAPER

A consumer sentiment factor from web content 

Asset Allocation and Asset Liability Management , Factor and Risk Modeling , Investing (Investment Management) , Portfolio Construction and Optimization , Risk Management

The explosion in alternative data has been a blessing and a curse to investment managers. We have identified one source that provided unique and uncorrelated information when added to analysis of traditional factors and other measures of sentiment. These consumer sentiment metrics may provide investors with additional transparency into sources of risk and return, and could potentially be used to create valuable new factors.

BLOG

Back-to-school (momentum) blues? 

Factor Investing , Models/Client Cases , Factors

The U.S. price momentum factor, which we highlighted for elevated crowding scores and vulnerability to negative performance at the end of June, suffered sizable drawdowns in the first seven trading days of September.

BLOG

Where were the (factor) crowds this summer? 

Factor Investing , Factors

When factors have historically become crowded, they’ve often experienced significant drawdowns in subsequent months. Which factors were relatively crowded at the end of 2018 — and how did they perform in the first half of 2019?

BLOG

More than a feeling: Quantifying consumer sentiment 

Factor Research Group , Factor Investing , Factors

Among a flood of alternative data sources, consumer sentiment based on citations online stood out.

PAPER

Peering into peer selection: Quantifying company similarity 

Asset Allocation and Asset Liability Management , Factor and Risk Modeling , Investing (Investment Management) , Performance Analysis , Portfolio Construction and Optimization , Risk Management

Peer selection plays a central role in many aspects of finance — including valuation, financial and competitive analysis, risk and portfolio modeling and ESG scoring and alpha generation. One common method of peers identification is industry classification, such as the Global Industry Classification Standard (GICS®). Here we ask if it’s possible to identify and measure relationships between companies from a systematic analysis of various types of data, including fundamentals, news and the text in company filings, and whether this data can help us better understand company relationships and the risks they may bring.

BLOG

Should we be surprised by earnings surprises? 

Factors , Factor Research Group , Factor Investing

Early 2019 earnings season has already contained a number of high-profile surprises, such as Facebooks's, but how predictable are these surprises, and what happens when earnings surprises return to trend?

BLOG

Equity markets in October – Has the tide turned? 

Models/Client Cases , Factor Indexes , Factor Investing

October’s market sell-off reflected investors’ concerns with the sustainability of economic growth, the longer-term impact of trade tariffs and rising interest rates. In all, it seemed to be a shift away from pro-cyclical themes. Do risks remain for those areas of the market?

PAPER

Is There an Options Sentiment Factor? 

Factor and Risk Modeling , Investing (Investment Management) , Portfolio Construction and Optimization , Risk Management , Asset Pricing and Valuation

We examine the trading activity and pricing structure in the equity options market to infer the sentiment of options traders on the underlying equity. We find that metrics constructed from the level of options trading activity relative to the underlying stock and from comparing the pricing of puts relative to calls at various moneyness levels have implications for the cross section of stock returns. Importantly, we also find that the information in options sentiment is additive and orthogonal to what is explained by other common style factors such as value and momentum, or by other measures of sentiment such as those derived from short interest or analyst revisions.

BLOG

Is momentum a crowded trade that is starting to unwind? 

Models/Client Cases , Factor Indexes , Factor Investing

The momentum factor has been on a tear the last year and a half. Is momentum a crowded trade that has started to unwind?

BLOG

Why is Tesla a short-selling target? 

Models/Client Cases , Integrated Risk Management , Factor Investing

Elon Musk, founder and CEO of Tesla, suggested in a series of tweets that going private could help Tesla avoid the scrutiny of quarterly reporting and pressure from short selling. Do companies targeted by short sellers share common characteristics? Could factor analysis help investors identify stocks that may become short-selling targets?

BLOG

All FAANGs are not created equal 

Factors , Factor Investing

FAANG stocks (Facebook, Apple, Amazon, Netflix and Google) make up nearly 40% of the NASDAQ 100 index, and smaller but significant weights in many others. Commonly grouped as tech stocks or growth companies, it seems reasonable to assume they share many similar characteristics. However, when examined through the lens of performance-driving factors, their characteristics are far from homogeneous.

PAPER

Anatomy of Hedge Fund Portfolios 

Measuring hedge funds’ positioning and potential crowding around stocks is of interest to many investors, given these funds’ reputation for outperformance. We explore the performance of hedge fund positions using MSCI HedgePlatform, which has advantages over U.S. Form 13F filings, including monthly data points, improved timeliness and full visibility of short positions.

PAPER

MSCI Integrated Factor Crowding Model 

Factor and Risk Modeling , Investing (Investment Management) , Risk Management

With the rise of factor investing, institutional investors increasingly have sought to understand whether their factor exposures are crowded. Current MSCI Barra equity factor risk models are designed to provide insight and detail to help institutional investors understand how a portfolio is positioned and what has driven its risk and return. The MSCI Integrated Factor Crowding Model is designed to complement the Barra model by providing investors with insight into how the rest of the market is positioned with respect to factors. The model examines crowding using a range of metrics, combining these into one standardized measure of factor crowding.

BLOG

Creating a common language for factor investing 

Factor Investing

Investors need a clear and consistent way to talk about factors. For more than 40 years, MSCI has defined how investors use factors to analyze risk and return, from individual stocks to entire portfolios. Factors are important drivers of portfolio performance and are well documented in academic research. They are used to quantify how much risk and return is attributable to different countries, sectors and styles.

PAPER

Introducing MSCI FaCS 

Factor and Risk Modeling , Investing (Investment Management) , Portfolio Construction and Optimization , Risk Management

Factors are important systematic sources of risk and return in equity portfolios. Given the pervasive use of factors via both active and indexed strategies, a standard approach is needed for defining factors and evaluating the factor characteristics of portfolios. We introduce MSCI FaCS, a classification standard and framework for analyzing and reporting of style factors in equity portfolios that is based on the Barra Global Total Market Equity Model for Long-Term Investors. Managers can use the framework to analyze and report factor characteristics, while investors and consultants can use its data to compare funds using common definitions.

PAPER

Is There a Short Interest Factor? 

Factor and Risk Modeling , Investing (Investment Management) , Portfolio Construction and Optimization , Risk Management

We introduce a new integrated short interest factor that combines multiple dimensions of short interest. The new factor combines information on the amount of shorting activity in the securities-lending market, the available lending supply, the rates investors are paying to short a security (borrow rates) and an adjustment for shorting activity due to dividend arbitrage. We find that dividend-arbitrage strategies can create large biases in short interest factors, particularly in Europe. We also find that short interest is a robust factor that provides unique explanatory power in the cross section of stock returns beyond what is explained by other well-known factors in every major market region.

BLOG

Why is “fear” missing from the “fear index”? 

Although global uncertainties remain high, the CBOE VIX Index — also known as the “fear index,” recently reached its lowest level since 1993. Some observers have questioned whether VIX remains a reliable indicator.