Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Is the Federal Reserve Causing Funds to Underperform? A causal machine learning analysis

Trindade Leite, Willian LU and Serenhov, Oliver LU (2022) DABN01 20221
Department of Statistics
Department of Economics
Abstract
Macroeconomic conditions heavily influence financial markets, and the leading corpus of theory in the field lays out some general principles observed by investors and asset managers alike. However, while the theory is sound, it is hard to measure how much effect these conditions have. To better understand this scenario, this study uses a novel technique that combines traditional causal inference with machine learning techniques to measure macroeconomic policy effects in the financial market. Specific to this study, the double machine learning framework measures the average treatment effect of the US Federal Reserve System’s interest rate’s growth rate on fixed income and equity funds returns. The period studied is from January 1986 to... (More)
Macroeconomic conditions heavily influence financial markets, and the leading corpus of theory in the field lays out some general principles observed by investors and asset managers alike. However, while the theory is sound, it is hard to measure how much effect these conditions have. To better understand this scenario, this study uses a novel technique that combines traditional causal inference with machine learning techniques to measure macroeconomic policy effects in the financial market. Specific to this study, the double machine learning framework measures the average treatment effect of the US Federal Reserve System’s interest rate’s growth rate on fixed income and equity funds returns. The period studied is from January 1986 to December 2021, as it includes data from many relevant events that caused interest rates to change around the world. Furthermore, the data is separated into two main clusters, i.e., passively and actively managed funds, since finance theory indicates that the latter should be less affected by a central bank’s interest rate changes.
As the double machine learning framework can use virtually any statistical learning procedure as a learner, two different techniques are tried in this study. Linear regression sets a baseline, and gradient boosting is used to assess what technique would produce better results. The results show some evidence of gradient boosting being a worthy technique for predicting returns and, therefore for the double machine learning procedure. The actively managed funds dataset results indicate that a 1% increase in the US Federal Reserve System’s interest rate led to a -11.97% decrease in actively managed fund returns. However, this effect must be considered alongside all others that might affect financial markets. The results indicate a rich field for future research that can serve investors and managers through data-driven decision-making. (Less)
Abstract (Portuguese)
As condições macroeconômicas influenciam fortemente os mercados financeiros, e o principal corpus teórico da área apresenta alguns princípios gerais observados por investidores e gestores de ativos. No entanto, embora a teoria seja sólida, é difícil medir quanto efeito essas condições têm. Para entender melhor esse cenário, este estudo usa uma nova técnica que combina inferência causal tradicional com técnicas de machine learning para medir os efeitos da política macroeconômica no mercado financeiro. Específico para este estudo, o método do double machine learning mede o efeito médio do tratamento da taxa de crescimento da taxa de juros do Sistema de Reserva Federal dos EUA nos retornos de fundos de renda fixa e ações. O período estudado é... (More)
As condições macroeconômicas influenciam fortemente os mercados financeiros, e o principal corpus teórico da área apresenta alguns princípios gerais observados por investidores e gestores de ativos. No entanto, embora a teoria seja sólida, é difícil medir quanto efeito essas condições têm. Para entender melhor esse cenário, este estudo usa uma nova técnica que combina inferência causal tradicional com técnicas de machine learning para medir os efeitos da política macroeconômica no mercado financeiro. Específico para este estudo, o método do double machine learning mede o efeito médio do tratamento da taxa de crescimento da taxa de juros do Sistema de Reserva Federal dos EUA nos retornos de fundos de renda fixa e ações. O período estudado é de janeiro de 1986 a dezembro de 2021, pois inclui dados de muitos eventos relevantes que causaram mudanças nas taxas de juros ao redor do mundo. Além disso, os dados são separados em dois clusters principais, ou seja, fundos geridos passiva e ativamente, uma vez que a teoria de finanças indica que este último deve ser menos afetado pelas mudanças nas taxas de juros de um banco central.
Como o método de double machine learning pode usar praticamente qualquer procedimento de aprendizado estatístico como motor, duas técnicas diferentes são tentadas neste estudo. A regressão linear define um benchmark e o gradient boosting com árvores de decisão é usado para avaliar qual técnica produziria melhores resultados. Os resultados mostram algumas evidências de que o gradient boosting é uma técnica válida para prever retornos e, portanto, para o procedimento do double machine learning. Os resultados do conjunto de dados de fundos gerenciados ativamente indicam que um aumento de 1% na taxa de juros do Sistema de Reserva Federal dos EUA levou a uma redução de -11,97% nos retornos dos fundos gerenciados ativamente. No entanto, este efeito deve ser considerado em conjunto com todos os outros que possam afetar os mercados financeiros. Os resultados indicam um campo rico para pesquisas futuras que podem atender investidores e gestores por meio de tomadas de decisão orientadas por dados. (Less)
Please use this url to cite or link to this publication:
author
Trindade Leite, Willian LU and Serenhov, Oliver LU
supervisor
organization
alternative title
A Reserva Federal Está Causando Desempenho Inferior aos Fundos de Investimento? Uma análise de machne learning causal
course
DABN01 20221
year
type
H1 - Master's Degree (One Year)
subject
keywords
Causal inference, actively managed funds, passively managed funds, gradient boosting, double machine learning
language
English
id
9083763
date added to LUP
2022-06-08 12:51:45
date last changed
2022-10-10 16:06:16
@misc{9083763,
  abstract     = {{Macroeconomic conditions heavily influence financial markets, and the leading corpus of theory in the field lays out some general principles observed by investors and asset managers alike. However, while the theory is sound, it is hard to measure how much effect these conditions have. To better understand this scenario, this study uses a novel technique that combines traditional causal inference with machine learning techniques to measure macroeconomic policy effects in the financial market. Specific to this study, the double machine learning framework measures the average treatment effect of the US Federal Reserve System’s interest rate’s growth rate on fixed income and equity funds returns. The period studied is from January 1986 to December 2021, as it includes data from many relevant events that caused interest rates to change around the world. Furthermore, the data is separated into two main clusters, i.e., passively and actively managed funds, since finance theory indicates that the latter should be less affected by a central bank’s interest rate changes.
As the double machine learning framework can use virtually any statistical learning procedure as a learner, two different techniques are tried in this study. Linear regression sets a baseline, and gradient boosting is used to assess what technique would produce better results. The results show some evidence of gradient boosting being a worthy technique for predicting returns and, therefore for the double machine learning procedure. The actively managed funds dataset results indicate that a 1% increase in the US Federal Reserve System’s interest rate led to a -11.97% decrease in actively managed fund returns. However, this effect must be considered alongside all others that might affect financial markets. The results indicate a rich field for future research that can serve investors and managers through data-driven decision-making.}},
  author       = {{Trindade Leite, Willian and Serenhov, Oliver}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Is the Federal Reserve Causing Funds to Underperform? A causal machine learning analysis}},
  year         = {{2022}},
}