USA

AgPa #67: Machine-Learned Manager Selection (3/4)

Selecting Mutual Funds from the Stocks They Hold: A Machine Learning Approach (2020)
Bin Li, Alberto G. Rossi
SSRN Working Paper, URL

The third AGNOSTIC Paper on the application of machine learning in manager selection. This week’s paper is very similar to AgPa #65 and AgPa #66, and again examines the data on US mutual funds. Despite somewhat different methodology, the results point in a similar direction. This, of course, increases the evidence that machine learning is actually useful for manager selection…

  • Machine learning helps to identify outperforming funds
  • The best and worst funds share common characteristics
  • Trading Frictions and Momentum are the most relevant variables

Read the Full Post

AgPa #66: Machine-Learned Manager Selection (2/4)

Machine Learning and Fund Characteristics Help to Select Mutual Funds with Positive Alpha (2023)
Victor DeMiguel, Javier Gil-Bazo, Francisco J. Nogales, Andre A. P. Santos
SSRN Working Paper, URL

The second AGNOSTIC Paper on the application of machine learning in manager selection. This week’s paper follows essentially the same idea as Kaniel et al. (2022) in AgPa #65. The authors also examine a comprehensive sample of US mutual funds and although they use slightly different methodology, arrive at generally similar conclusions. This, of course, increases the evidence that machine learning is indeed helpful for manager selection…

  • Machine learning helps to identify outperforming funds
  • Past performance and measures of activeness are the most relevant variables
  • Given their alpha, machine-selected funds remain too small

Read the Full Post

AgPa #65: Machine-Learned Manager Selection (1/4)

Machine-Learning the Skill of Mutual Fund Managers (2022)
Ron Kaniel, Zihan Lin, Markus Pelger, Stijn Van Nieuwerburgh
NBER Working Paper 29723, URL

To conclude the posts on manager selection, at least for the moment, I will dive into one of the most recent research frontiers in this area. Since the application of machine learning in investment management has been intensively studied among equities for more than three years now, it is not surprising that researchers also start to apply such algorithms to other asset classes. A natural candidate for this are equity mutual funds and this is exactly where this and the next four week’s AGNOSTIC Papers come in.

  • Machine learning helps to identify outperforming funds
  • Less is more – not all information is necessary
  • Alpha is easier to predict than total returns

Read the Full Post

AgPa #64: Fund Manager Multitasking

Managerial Multitasking in the Mutual Fund Industry (2023)
Vikas Agarwal, Linlin Ma, Kevin Mullally
Financial Analysts Journal 79(2), URL/SSRN

Some days ago, I came across yet another interesting study on manager selection. The idea of this week’s AGNOSTIC Paper is very straight forward. When you hire a fund manager, you want this person to focus on your money and not do much else. Probably no one would agree to a surgery where the surgeon operates on five patients at the same time. So why hire a fund manager who manages more than one fund?

  • Manager multitasking strongly increased from 1990 to 2018
  • Managers who start multitasking tend to have better track records
  • Fund performance decreases significantly after managers start multitasking
  • The number of managed funds amplifies the effect of multitasking
  • Investors put less money into existing funds of multitasking managers

Read the Full Post

AgPa #61: Minivans versus Sports Cars

Sensation Seeking and Hedge Funds (2018)
Stephen Brown, Yan Lu, Sugata Ray, Melvyn Teo
The Journal of Finance 73(6), 2871-2914, URL/SSRN

Tell me about the car you drive and I tell you who you are. In the hope of not offending the car enthusiasts too much, this week’s AGNOSTIC Paper relates the performance and characteristics of hedge fund managers to the type of car they drive. As announced in last week’s article, this is a funny example for the important soft factors that investors should consider when selecting an asset manager.

  • Sports car drivers take more risk and deliver lower performance
  • Funds of sports car drivers come with more operational risk
  • Sports-car-driving investors want sports-car-driving fund managers

Read the Full Post

AgPa #56: The Equity Risk Premium of Small Businesses

Small Business Equity Returns: Empirical Evidence from the Business Credit Card Securitization Market (2023)
Matthias Fleckenstein, Francis A. Longstaff
The Journal of Finance 78(1), URL

In 2020, there were more than 31M small private businesses in the US. Even though the estimated value of those businesses is “just” $12T, the sheer number is astonishing when compared to about 4,000 tradable US stocks (excluding penny stocks). For stocks, we typically use measures like returns, multiples, and volatilities. But given the lack of daily prices, it is difficult to calculate those measures for small private businesses. This week’s AGNOSTIC Paper is an attempt to change that…

  • Small businesses had an equity risk premium of 10.7% and a volatility of 56%
  • Robustness: the model generates plausible results for S&P 500 stocks

Read the Full Post

AgPa #52: Happier Employees, Better Returns?

Employee Satisfaction and Long-Run Stock Returns, 1984–2020 (2022)
Hamid Boustanifar, Young Dae Kang
Financial Analysts Journal 78(3), URL/SSRN

A common sales-pitch of ESG strategies is the idea that those strategies not only do good for the planet and other stakeholders, but also generate higher returns. I am generally skeptic about this, but there are studies showing that certain ESG variables historically indeed predicted higher returns. A prominent example for this is the paper on employee satisfaction by Alex Edmans (2011). This week’s AGNOSTIC Paper is an out-of-sample test of this study with somewhat more thorough testing.

  • “Best Companies” outperformed several benchmarks
  • “Best Companies” outperformed during crises and out-of-sample
  • Quality and Low-Risk factors explain some of the premium on “Best Companies”

Read the Full Post

AgPa #51: Short Sellers vs. Firms

Go Down Fighting: Short Sellers vs. Firms (2012)
Owen A. Lamont
The Review of Asset Pricing Studies 2(1), URL

I like controversial and (in my opinion) misunderstood topics and this week’s AGNOSTIC Paper examines the next big one: short selling. The paper is unfortunately already more than 10 years old, but it is still a go-to reference for short selling. Apart from that, the fights between firms and short sellers are also quite entertaining – at least from an outsider’s perspective…

  • Short-seller-fighting firms tend to massively underperform
  • The results are robust after controlling for the major factors

Read the Full Post

SA #18: RPV – ‘Pure Value’ Is Indeed More Value Than ‘Value’

RPV: 'Pure Value' Is Indeed More Value Than 'Value'
April 08, 2023

Summary

  • Systematic value investors bet that a diversified portfolio of fundamentally “cheap” stocks should outperform a portfolio of “expensive” stocks over the long term.
  • The Invesco S&P 500 Pure Value ETF tracks the S&P 500 Pure Value Index and was incepted in March 2006.
  • Compared to other “smart-beta” value ETFs, RPV is a more aggressive value-strategy and only invests in the top 20% value stocks of the S&P 500 universe (currently 82 positions).
  • With this methodology and three fundamental valuation ratios as value signals, the investment process underlying RPV incorporates several best-practices from the academic literature on the value-factor.
  • RPV is well positioned in a value-peer group and (in my opinion) a very good instrument for investors seeking concentrated exposure to the value-factor.


Read the Full Article on Seeking Alpha

Read the Full Post

AgPa #48: Investable Machine Learning for Equities

Investable and Interpretable Machine Learning for Equities (2022)
Yimou Li, Zachary Simon, David Turkington
The Journal of Financial Data Science Winter 2022, 4(1), URL

Regular readers of this blog know that machine learning in asset management is one of my favorite topics and I recently found new interesting material. This week’s AGNOSTIC Paper is the first of two studies and examines an important issue with machine learning models in great detail: interpretability…

  • Machine learning models outperform simpler methods
  • Different models learn different investment approaches

Read the Full Post