IDEAS home Printed from https://ideas.repec.org/h/spr/sprchp/978-3-031-48169-7_13.html
   My bibliography  Save this book chapter

The Future of Investment Practice, Artificial Intelligence, and Machine Learning

In: Professional Investment Portfolio Management

Author

Listed:
  • James W. Kolari

    (Mays Business School, Texas A&M University)

  • Wei Liu

    (Mays Business School, Texas A&M University)

  • Seppo Pynnönen

    (University of Vaasa)

Abstract

Quantitative methods are increasingly becoming an important ingredient in professional investment practice. Markowitz (Journal of Finance 7:77–91, 1952, Portfolio selection: Efficient diversification of investments. John Wiley & Sons, New York, NY, 1959) laid the foundation of modern investment management with the invention of the mean-variance investment parabola. During the time of this writing, Nobel Prize laureate Harry Markowitz passed away on June 22, 2023. His landmark diversification concepts, which are grounded in mathematics and statistics, forever changed investment practice. Professional managers are careful to make sure that their portfolios contain securities or other assets that together reduce their risk. He once remarked that diversification is the only free lunch in the market. In other words, investors can use diversification to reduce the risk of their investment portfolios. He advised that investors should seek to maximize returns per unit risk, not returns per se. In this book, we have sought to build upon the foundation that Markowitz established. At the center of our analyses is the ZCAPM of Kolari, Liu, and Huang. The ZCAPM is derived from Markowitz’s mean-variance investment parabola in combination with Black’s (Journal of Business 45:444–454, 1972) zero-beta CAPMBlack’s zero-beta CAPM. Unfortunately, the dream of building portfolios that lie on the efficient frontier of the parabola has eluded academic and professional researchers. It turns out that problems with estimating expected returnsExpected returns in the future for securities as well as the covarianceCovariance matrix for a large number of securities have been more difficult than anticipated. Departing from this traditional portfolio approach, we break new ground by taking a different approach to building high performing stock portfolios—namely, we apply the ZCAPM asset pricing model. As documented in this book, our efforts have paid off by creating portfolios that form an empirical investment parabola consistent with the theoretical parabola of Markowitz. In their 2021 book, Kolari, Liu, and Huang documented extensive evidence to prove that the empirical ZCAPMEmpirical ZCAPM dominates multifactor models in standard, out-of-sample Fama and MacBeth (Journal of Political Economy 81:607–636, 1973) cross-sectional regressionCross-sectional regression tests. Given the remarkable empirical success of the ZCAPM, the authors performed a limited set of experiments to show that the ZCAPM could be applied to portfolio construction. Using the model, relatively high performing stock portfolios were built. In the present book, we substantially expand these portfolio experiments. Extending their previous analyses, we began by building a proxy for the global minimum variance portfolio GGlobal minimum variance portfolio G that pins the mean-variance parabola in return/risk spaceReturn/risk space. We then employed portfolio G to compute the two factors for the empirical ZCAPMEmpirical ZCAPM: (1) average market returns related to beta risk; and (2) cross-sectional return dispersionCross-sectional return dispersion associated with zeta risk. Stocks were sorted on beta and zeta risks to form portfolios. Portfolios were built by optimally weighting the individual stocks. Finally, one-month-ahead returns for the portfolios were computed on an out-of-sample basis to be consistent with real world investor experience. Portfolio performance was evaluated in detail, including average annual returns, Sharpe ratios, and various risk metrics. In general, our findings showed that empirically efficient portfoliosEfficient portfolio can be produced that well outperform general market indexes, such as the CRSP index and S &P 500 indexS &P 500 index. Since most professional managers cannot consistently beat these general market indexes over time (e.g., three-to-five-year periods of time), our results are noteworthy. Also, we applied the ZCAPM to the problem of building high-performing equity mutual fund portfolios. In sum, our portfolio results showed that investors would benefit from machine-made stock and equity mutual fund portfolios based on the ZCAPM. The authors encourage cooperation with the professional investment community to implement these portfolios in the real world.

Suggested Citation

  • James W. Kolari & Wei Liu & Seppo Pynnönen, 2023. "The Future of Investment Practice, Artificial Intelligence, and Machine Learning," Springer Books, in: Professional Investment Portfolio Management, chapter 0, pages 237-247, Springer.
  • Handle: RePEc:spr:sprchp:978-3-031-48169-7_13
    DOI: 10.1007/978-3-031-48169-7_13
    as

    Download full text from publisher

    To our knowledge, this item is not available for download. To find whether it is available, there are three options:
    1. Check below whether another version of this item is available online.
    2. Check on the provider's web page whether it is in fact available.
    3. Perform a search for a similarly titled item that would be available.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:sprchp:978-3-031-48169-7_13. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.