No Cover Image

Journal article 40 views 8 downloads

Fund performance evaluation with explainable artificial intelligence

Raghav Kovvuri, Hsuan Fu Orcid Logo, Xiuyi Fan Orcid Logo, Monika Seisenberger Orcid Logo

Finance Research Letters, Volume: 58, Start page: 104419

Swansea University Authors: Raghav Kovvuri, Xiuyi Fan Orcid Logo, Monika Seisenberger Orcid Logo

  • 64512.pdf

    PDF | Version of Record

    © 2023 The Authors. This is an open access article under the CC BY license.

    Download (1.07MB)

Abstract

We apply explainable artificial intelligence (xAI) to a large dataset of global equity funds. Our approach combines the XGBoost model with Shapley values; the former is a machine learning framework that enhances model fitness while the latter is an xAI method that provides informed explanations rega...

Full description

Published in: Finance Research Letters
ISSN: 1544-6123
Published: Elsevier BV 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa64512
Abstract: We apply explainable artificial intelligence (xAI) to a large dataset of global equity funds. Our approach combines the XGBoost model with Shapley values; the former is a machine learning framework that enhances model fitness while the latter is an xAI method that provides informed explanations regarding the direction and significance of predictors. Based on macro-finance and fund-level factors, our fund performance evaluation of G10 countries uncovers novel insights into the diversification of country portfolios: both over- and under-diversification are associated with poor performance. Our analysis establishes consistency through a benchmark linear regression model and robustness at country level.
Keywords: Global Open-Ended Funds; Country Portfolios; Herfindahl-Hirschman Index; SHapley Additive exPlanations; Machine Learning; eXtreme Gradient Boosting
College: Faculty of Science and Engineering
Funders: H. Fu gratefully acknowledges financial support from the Social Sciences and Humanities Research Council of the Government of Canada and the AMF–GIRIF Fund at Laval University. H. Fu also thanks the grant from the Program of financial support to faculties for knowledge mobilization activities and the dissemination and promotion of research results, from Presses de l’Université Laval Development Fund. We all gratefully acknowledge financial support from the cooperation programme between the governments of Quebec and Wales, and honor the financial support we received for knowledge exchange in the Horizon 2020 project CID.
Start Page: 104419