Forest Through the Trees: Building Cross-Sections of Stock Returns

Bryzgalova, Svetlana; Pelger, Markus; Zhu, Jason

doi:10.2139/ssrn.3493458

Cited by 46 publications

(32 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Decision and regression trees are another popular class of ML methods employed in generating multifactor signals. In fact, Bryzgalova, Pelger, and Zhu (2019) point out that the standard factor models of Fama andFrench (1993, 2015) can be viewed as simple tree models with just two splitting points based on the quantiles of the distributions of company fundamentals, such as the book to price ratio or operating profitability. Coqueret and Guida (2018) produce tree-based forecasts of the returns of a large set of US equities between 2002 and 2016 using extreme gradient-boosted trees.…”

Section: Building Multifactor Signalsmentioning

confidence: 99%

Machine Learning for Active Portfolio Management

Bartram

Branke

Rossi³

et al. 2021

JFDS

View full text Add to dashboard Cite

KEY FINDINGSn Machine learning (ML) methods have several advantages that can lead to successful applications in active portfolio management, including the ability to capture nonlinear patterns and a focus on prediction through ensemble learning.n ML methods can be applied to different steps of the investment process, including signal generation, portfolio construction, and trade execution, with reinforcement learning expected to play a more significant role in the industry.n Empirically, the investment performance of ML-based active exchange-traded funds is mixed.

show abstract

Section: Building Multifactor Signalsmentioning

confidence: 99%

Machine Learning for Active Portfolio Management

Bartram

Branke

Rossi³

et al. 2021

JFDS

View full text Add to dashboard Cite

show abstract

“…These patterns are then mapped into mathematical logic, generating information on statistical relationships between observations. Typical use cases are the de-noising of large datasets ( Ng, 2017 ) or asset clustering ( Bryzgalova et al, 2020 ). In supervised learning tasks, an algorithm infers a mapping from inputs to output based on example pairs.…”

Section: Ai and How Financial Complexity Affects Itmentioning

confidence: 99%

Artificial Intelligence and Systemic Risk

2019

View full text Add to dashboard Cite

Artificial intelligence (AI) is rapidly changing how the financial system is operated, taking over core functions for both cost savings and operational efficiency reasons. AI will assist both risk managers and the financial authorities. However, it can destabilize the financial system, creating new tail risks and amplifying existing ones due to procyclicality, unknown-unknowns, the need for trust, and optimization against the system.

show abstract

“…Regularization methods such as elastic net and tree-based methods, such as gradient boosting and random forests, have been applied to solve several problems in Finance (e.g. Rapach et al, 2013;Bryzgalova et al, 2019;Coulombe et al, 2020;Freyberger et al, 2020;Kozak et al, 2020). We choose these methods because they have been shown to outperform other ML algorithms in forecasting economic and financial variables with structured (or tabular) data, as in our case (e.g.…”

Section: Introductionmentioning

confidence: 99%

Can Machine Learning Help to Select Portfolios of Mutual Funds?

et al. 2021

View full text Add to dashboard Cite

Identifying outperforming mutual funds ex-ante is a notoriously difficult task. We use machine learning methods to exploit the predictive ability of a large set of mutual fund characteristics that are readily available to investors. Using data on US equity funds in the 1980-2018 period, the methods allow us to construct portfolios of funds that earn positive and significant out-of-sample risk-adjusted after-fee returns as high as 4.2% per year. We further show that such outstanding performance is the joint outcome of both exploiting the information contained in multiple fund characteristics and allowing for flexibility in the relationship between predictors and fund performance. Our results confirm that even retail investors can benefit from investing in actively managed funds. However, we also find that the performance of all our portfolios has declined over time, consistent with increased competition in the asset market and diseconomies of scale at the industry level.

show abstract

Forest Through the Trees: Building Cross-Sections of Stock Returns

Cited by 46 publications

References 40 publications

Machine Learning for Active Portfolio Management

Machine Learning for Active Portfolio Management

Artificial Intelligence and Systemic Risk

Can Machine Learning Help to Select Portfolios of Mutual Funds?

Contact Info

Product

Resources

About