Volume 23, No. 3, Third Quarter 2025

Practitioner’s Digest • Vol. 23, No. 3

The “Practitioners Digest” emphasizes the practical significance of manuscripts featured in the “Insights” and “Articles” sections of the journal. Readers who are interested in extracting the practical value of an article, or who are simply looking for a summary, may look to this section.

A Transparent Alternative to Neural Networks with an Application to Predicting Volatility

by: Megan Czasonis, Mark Kritzman and David Turkington

Many prediction tasks in economics and finance involve complicated relationships that lie beyond the reach of linear regression analysis. Neural networks can capture these complex dynamics, but they are notoriously opaque and difficult to implement. We show that an alternative model-free prediction method, called relevance-based prediction, captures many of the same complex dynamics as neural networks, but with transparency into how each observation contributes to each prediction and how each predictive variable contributes to the reliability of each prediction. We describe both prediction methods and compare their respective efficacy for predicting stock market volatility.

Building Net Zero Portfolios of Sovereign Bonds

by: Gong Cheng, Eric Jondeau and Benoît Mojon

We propose a method for creating a sovereign securities portfolio that gradually reduces its carbon footprint, in line with the Paris Agreement. This allows passive investors to achieve netzero (NZ)targets while maintaining risk-adjusted returns similar to a business-as-usual benchmark. From 2015 to 2021, our approach would have cut carbon intensity by 34.7% with a 7.5% yearly target, compared to just an 8.5% reduction for the benchmark. Total emissions would have dropped by 27.5%, while they would have risen by 25.4% in the benchmark. Notably, NZ portfolios match the benchmark’s financial performance and creditworthiness without significant foreign exchange risks

Optimizing Large Language Models for Sustainable Investors

by: Andrew Chin, Che Guan, Promod Rajaguru, Qifeng Sun and Yuning Wu

We use large language models (LLMs) and natural language processing (NLP) to extract environmental, social and governance (ESG) insights from real-time news, creating an expert-annotated dataset to evaluate ESG classification, firm relevance, and sentiment. Our fine-tuned models outperform pre-trained ones in ESG detection, firm impact, and sentiment analysis. Furthermore, in-context learning does not improve performance, indicating optimal tuning. Event studies and back tests show that our sentiment signals predict underperforming stocks, with higher model confidence in negative sentiment correlating to worse outcomes. These findings emphasize the value of fine-tuning models with expert annotated data, and leveraging ESG sentiment signals to generate investment insights from qualitative data to enhance alpha generation.

Volatility Managed Multi-Factor Portfolios

by: Christoph Reschenhofer and Josef Zechner

This paper demonstrates that portfolio performance can be substantially enhanced by simultaneously utilizing historical factor return volatilities and option-derived market volatilities to optimize factor exposures. The improvements are particularly pronounced in regimes where option-implied market returns exhibit high volatility and right-skewness. Further gains in risk-adjusted portfolio returns are achieved by estimating model parameters separately for different regimes. Qualitatively similar results are obtained when all parameters are estimated strictly out-of-sample. These findings are not limited to a specific set of factors; comparable enhancements are observed when employing principal components derived from a broad set of factors.

Network Models in Finance: Expanding the Tools for Portfolio and Risk Management

by: Frank J. Fabozzi and Gueorgui S. Konstantinov • reviewed by: Mullika Sahrawat

“Book Reviews” identifies important, and often popular, new books from a wide range of investment topics. Beyond providing a summary and review of the content and style of the books, “Book Reviews” seeks to contribute to a conscious, critical, and informed approach to investment literature.