AgPa #49: Machine Learning in Quant Asset Management

How Can Machine Learning Advance Quantitative Asset Management? (2023)
David Blitz, Tobias Hoogteijling, Harald Lohre, Philip Messow
The Journal of Portfolio Management Quantitative Tools 2023, URL/SSRN

This week’s AGNOSTIC Paper is a broad overview about machine learning in investment management. The authors outline the benefits and pitfalls of machine learning compared to “traditional” econometrics and present several use cases in the world of (quantitative) asset management. They also provide ideas for research governance to keep those powerful methods under control.

  • Benefits and pitfalls of machine learning in finance
  • Use cases of machine learning in asset management
  • Keeping it under control: research governance and protocol

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

SA #17: IUSV – Transparent Value With Modest Active Risk

IUSV: Transparent Value With Modest Active Risk
March 29, 2023

Summary

  • The general idea behind the value factor is that a diversified portfolio of fundamentally cheap stocks should outperform over the long term.
  • Since January 2017, the iShares Core S&P U.S. Value ETF has tracked the S&P 900 Value Index and provides transparent exposure to the well-researched value premium.
  • S&P uses three well-known fundamental valuation ratios to identify and overweight “cheap” value stocks with respect to the overall market index.
  • Relying on multiple value signals is in line with the research consensus of the literature on the value factor and differentiates IUSV from some competitors.
  • Despite the recent value drawdown, IUSV kept up with a peer group and should be a reasonable instrument for investors who want to have U.S. large-cap value exposure at modest active risk.


Read the Full Article on Seeking Alpha

Read the Full Post

SA #16: IWD – Low Growth Is Not Necessarily Value – Also For Large Caps

IWD: Low Growth Is Not Necessarily Value – Also For Large Caps
March 27, 2023

Summary

  • There are countless methods and nuances of (systematic) value investing, but the general idea remains “cheap beats expensive”. Not always, but on average over the long run.
  • The iShares Russell 1000 Value ETF tracks the Russell 1000 Value Index and offers a simple, transparent, and cheap implementation of the value premium for US large caps.
  • The Russell value process unfortunately equates “low sales growth” with “value” which contradicts with the best practices discussed in the literature on the value factor.
  • Despite decent performance when compared to an investable value peer-group, IWD is therefore not my preferred value implementation.


Read the Full Article on Seeking Alpha

Read the Full Post

AgPa #47: Equity Factors without Shorting

When Equity Factors Drop Their Shorts (2020)
David Blitz, Guido Baltussen, Pim van Vliet
Financial Analysts Journal, 76(4), URL

This week’s AGNOSTIC Paper examines the important issue of performance contributions from the long and short legs of the major factor premiums. In English: can we profitably invest in factors without shorting a large number of stocks?

  • The long-legs of factors are more important than the short-legs
  • The same pattern holds in international markets

Read the Full Post

AgPa #46: Transaction Costs and Capacities of Factor Strategies

Transaction Costs of Factor-Investing Strategies (2019)
Feifei Li, Tzee-Man Chow, Alex Pickard, Yadwinder Garg
Financial Analysts Journal 75(2), 47-61, URL

In this week’s AGNOSTIC paper, the authors develop a transaction cost model and use it to estimate the capacity of the major factors. There are many ways to define capacity in more detail, but the general idea is quite simple. It is the amount of money you can invest in a profitable strategy before you move prices too much and lose your advantage. Unfortunately, what theoretically sounds simple and intuitive is actually quite difficult to estimate in practice…

  • Implementation costs depend on tilt, turnover, and execution speed
  • Capacities of factors for a maximum cost of 0.5% per year
  • There is not yet a consensus on factor capacities

Read the Full Post

AgPa #45: Factor Investing in Private Debt

Investing with Style in Liquid Private Debt (2022)
Thomas Mählmann, Galina Sukonnik
Financial Analysts Journal 78(3), URL

This week’s AGNOSTIC Paper is yet another out-of-sample test of the Momentum and Value factor. The authors apply the factors within the relatively new asset class of private debt. More specifically, for “[…] loans to non-investment grade issuers, commonly known as leveraged loans.” This is obviously not my main area of expertise, but I learned from the paper that there is quite some trading of such loans in private secondary markets. Implementing a factor strategy for leveraged loans is obviously more complicated than for equities, but this is exactly what makes this study so interesting.

  • Private debt improves multi-asset portfolios
  • Value and Momentum are profitable within private debt

Read the Full Post

AgPa #44: Betting against Quant – Thematic Indices

Betting against Quant: Examining the Factor Exposures of Thematic Indexes (2021)
David Blitz
The Journal of Beta Investment Strategies Winter 2021, URL/SSRN

This week’s AGNOSTIC Paper examines a recent trend in the asset management industry: thematic indices. The sales pitch is simple. With a thematic index you can easily invest in the “next big things”. Artificial intelligence, aging population, e-sports and gaming, healthcare breakthroughs – just name your buzzword and you will find an investment product for it. This week’s paper is among the first that examine such thematic investments through the lens of the major factor premiums.

  • Thematic indices are more volatile and have higher betas than the overall market
  • Thematic indices tend to hold expensive, low-quality stocks with neutral momentum
  • There are still reasons why thematic indices exist

Read the Full Post

SA #15: VLUE – Transparent Value With Little Industry Bets

VLUE: Transparent Value With Little Industry Bets
February 28, 2023

Summary

  • The core idea of value investing remains unchanged since its introduction by Graham and Dodd in the 1930s: fundamentally cheap stocks tend to beat expensive stocks on average.
  • The iShares Edge MSCI USA Value Factor ETF tracks the MSCI USA Enhanced Value Index and provides cheap, efficient, and transparent systematic value exposure among US large caps.
  • Importantly, the underlying value index incorporates several insights of the literature on the value factor (multiple value signals, value-rankings within sectors, and no unintended industry bets).
  • For investors who want US value exposure without running into unintended sector bets and without taking too much active risk, VLUE is an interesting instrument.


Read the Full Article on Seeking Alpha

Read the Full Post