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.
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.
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.
Onze onderzoekers publiceren veel whitepapers die zijn gebaseerd op hun eigen empirische onderzoek, maar ze kijken ook naar kwantitatief onderzoek dat door anderen is gedaan. David Blitz, hoofd Quant Equities Research, vertelt over opvallende externe papers.