australiaen
A backtesting protocol in the era of machine learning

A backtesting protocol in the era of machine learning

08-08-2019 | From the field

Is machine learning really a game changer for finance? This paper1 by three renowned finance professors discusses the implications of machine learning for investment management.

  • David Blitz
    David
    Blitz
    Head of Quant Research

They argue that machine learning provides a set of powerful tools that holds considerable promise for investment management, but that the danger of misapplying these techniques can lead to disappointment.

Stay informed on our latest insights with monthly mail updates
Stay informed on our latest insights with monthly mail updates
Subscribe

One crucial limitation involves data availability. Many of machine learning’s early successes originated in the physical and biological sciences, in which truly vast amounts of data are available. Machine learning applications often require far more data than are available in finance, which is of particular concern in longer-horizon investing. Hence, choosing the right applications before applying the tools is important.

In addition, capital markets reflect the actions of people, which may be influenced by others’ actions and by the findings of past research. The authors address these concerns by proposing a research protocol that pertains both to the application of machine learning techniques and to quantitative finance in general. Their guidelines bear a lot of resemblance to the principles in the investment philosophy that we already adhere to for our quantitative strategies.

1 Arnott, Harvey & Markowitz, “A Backtesting Protocol in the Era of Machine Learning”, working paper, 2018.

From the field
From the field

Our researchers publish many whitepapers based on their own empirical studies; they also follow quantitative research done by others.

Read all articles
Subjects related to this article are:

Disclaimer

BY CLICKING ON “I AGREE”, I DECLARE I AM A WHOLESALE CLIENT AS DEFINED IN THE CORPORATIONS ACT 2001.

What is a Wholesale Client?
A person or entity is a “wholesale client” if they satisfy the requirements of section 761G of the Corporations Act.
This commonly includes a person or entity:

  • who holds an Australian Financial Services License
  • who has or controls at least $10 million (and may include funds held by an associate or under a trust that the person manages)
  • that is a body regulated by APRA other than a trustee of:
    (i) a superannuation fund;
    (ii) an approved deposit fund;
    (iii) a pooled superannuation trust; or
    (iv) a public sector superannuation scheme.
    within the meaning of the Superannuation Industry (Supervision) Act 1993
  • that is a body registered under the Financial Corporations Act 1974.
  • that is a trustee of:
    (i) a superannuation fund; or
    (ii) an approved deposit fund; or
    (iii) a pooled superannuation trust; or
    (iv) a public sector superannuation scheme
    within the meaning of the Superannuation Industry (Supervision) Act 1993 and the fund, trust or scheme has net assets of at least $10 million.
  • that is a listed entity or a related body corporate of a listed entity
  • that is an exempt public authority
  • that is a body corporate, or an unincorporated body, that:
    (i) carries on a business of investment in financial products, interests in land or other investments; and
    (ii) for those purposes, invests funds received (directly or indirectly) following an offer or invitation to the public, within the meaning of section 82 of the Corporations Act 2001, the terms of which provided for the funds subscribed to be invested for those purposes.
  • that is a foreign entity which, if established or incorporated in Australia, would be covered by one of the preceding paragraphs.
I Disagree