Cleaning Out The Factor Zoo

The explosion of financial research in recent years has uncovered an expanding assortment of alpha-generating possibilities that presumably offer a shortcut for enhancing returns over and above a market index. But as a growing list of studies reminds, you can drive a bus through the gap between the reported laundry list of factors and those that pass the smell test.

A statistically robust anomaly is a thing to behold, but such creatures are as rare as bluebirds in winter. Some researchers are keen to point out that while it’s easy to find what appears to be a mother lode of alpha-generating factors, the ones that actually work in practice – after deducting trading costs, adjusting for data mining effects, etc. – are a tiny subset.

Research Affiliates recently noted that “researchers have identified hundreds of factors that purport to predict equity returns; we find a half dozen that provide an opportunity to outperform the market” — value, low beta, profitability, investment, momentum, and size.

The challenge of sorting through the proliferation of factors requires a new set of tools. “Organizing this ‘zoo of factors’ and distinguishing between useful, useless, and redundant factors require econometric techniques that can deal with the curse of dimensionality,” advises a recent paper from three authors at the University of Chicago. In a bid to navigate the ever-expanding zoo, they outline a model-selection methodology to wade through the morass and separate the wheat from the chaff.

A book published last year by Andrew L. Berkin and Larry E. Swedroe offers a similar if somewhat less technical screening process in Your Complete Guide to Factor-Based Investing: The Way Smart Money Invests Today. A genuinely robust factor must be persistent, pervasive, robust, investable, and intuitive, they write. Just eight survive the gauntlet: market beta, size, value, momentum, profitability, quality, term, and carry.

Perhaps the most ambitious screening effort yet in the factor zoo research is the “Replicating Anomalies” paper from the Fisher College of Business at Ohio State University. A revised version dated April 2017 outlines the results from analyzing 447 return anomalies for equities that, on first glance, appear to offer market-beating features. But as the authors conclude, “capital markets are more efficient than previously recognized.”

The paper’s key findings:

After we control for microcaps with NYSE breakpoints and value-weighted returns, 286 anomalies (64%) are insignificant at the conventional 5% level. Imposing the t-value cutoff of three increases the number of insignificance further to 380 (85%). In the trading frictions category that contains mostly liquidity variables, 95 out of 102 (93%) are insignificant at the 5% level. The distress anomaly is also virtually nonexistent in our replication. Even for significant anomalies, such as price momentum and operating accruals, their magnitudes are often much lower than originally reported. Finally, out of the 161 significant anomalies, the q-factor model leaves 115 alphas insignificant (150 with t < 3). In all, our evidence suggests that capital markets are more efficient than previously reported.

Surprising? Not really. Unless you’ve been living on Mars, it’s been clear for several decades that beating an index that’s relevant for a strategy under scrutiny is difficult, particularly after adjusting for taxes and trading costs. Smart beta and related indexing efforts try to tweak this reality by developing superior benchmarks. There have been successes on this front, but far fewer than it appears.

Another twist on this point arrived with the admission last week by Ted Seides that he lost his 2007 bet with uber-investor Warren Buffett that the S&P 500 would trail a mix of carefully selected hedge funds.

Nine years ago, Warren Buffett and I made a 10-year charitable wager that pitted the returns of five funds of hedge funds against a Standard & Poor’s 500 index fund. With eight months remaining, for all intents and purposes, the bet is over. I lost.

There’s a lesson here for dealing with the factor zoo. It’s fun to look at the animals, but be careful about getting too close to the cages and exposing your hands (or assets) to the beasts. A few are tame, but many if not most will bite.

One thought on “Cleaning Out The Factor Zoo

  1. Pingback: The Explosion of Financial Research -

Comments are closed.