Sustainable Portfolio Construction via Machine Learning: ESG, SDG and Sentiment
Authors:
Open Access
- 18 November 2024
- journal article
- research article
- Published by Wiley in European Financial Management
- Vol. 31 (3) , 1148-1169
Abstract
This study proposes portfolio construction strategies based on novel sentiment, ESG and SDG scores. We utilize natural language processing to establish a novel daily score system that mitigates concerns of different rating standards. The portfolios constructed are optimized via machine learning algorithms on a monthly basis using daily historical returns. Utilizing the equal‐weighted portfolios as benchmarks, we empirically show that our optimized portfolios exhibit better trading performance in both the SPX500 and STOXX600 indices. The findings demonstrate that nonlinear models such as random forests, neural networks, and genetic algorithms can perform better than other machine learning models in portfolio management.Keywords
This publication has 99 references indexed in Scilit:
- Out‐of‐sample volatility prediction: Rolling window, expanding window, or both?Journal of Forecasting, 2023
- Does model complexity add value to asset allocation? Evidence from machine learning forecasting modelsJournal of Applied Econometrics, 2021
- Dynamic factor model with infinite‐dimensional factor space: ForecastingJournal of Applied Econometrics, 2018
- Every Little Helps? ESG News and Stock Market ReactionJournal of Business Ethics, 2017
- The Opportunity Cost of Negative Screening in Socially Responsible InvestingJournal of Business Ethics, 2015
- Does it Really Hurt to be Responsible?Journal of Business Ethics, 2013
- Corporate social responsibility and access to financeStrategic Management Journal, 2013
- Capabilities, Proactive CSR and Financial Performance in SMEs: Empirical Evidence from an Australian Manufacturing Industry SectorJournal of Business Ethics, 2011
- Australian Socially Responsible Funds: Performance, Risk and Screening IntensityJournal of Business Ethics, 2011
- Support-vector networksMachine Learning, 1995