Special Issue on Data Science in Quantitative Finance, Actuarial Science, and Sustainable Finance

Introduction:

Over the past decade, data science techniques—particularly machine learning (ML) and artificial intelligence (AI)—have rapidly transformed research and practice in quantitative finance, actuarial science, and sustainable finance. Applications now span algorithmic trading, portfolio optimization, mortality forecasting, insurance risk modeling, and ESG analytics. ML and AI are increasingly used to evaluate climate risk, process unstructured disclosures, develop carbon pricing tools, and assess green taxonomies. Natural language processing, satellite data, and IoT sensors further enhance sustainable investment strategies and regulatory compliance.

Recent applications include predicting asset prices (Gu et al., 2020, Brogaard & Zareei, 2022), robo-advising (D’Acunto & Ross, 2019), AI of stock analyses (Cao et al., 2024), managing portfolios (Chen et al., 2023), mutual fund selection (DeMiguel, 2023), forecasting earnings (De Silva & Thesmar, 2024), making lending decisions (Liu, 2022), and estimating bank risk (Hanley & Hoberg, 2019). Meanwhile, Farboodi et al. (2025) investigated the valuation of financial data and Bartlett et al. (2025) use proprietary data to study the missing odd-lot quotes. Using data on social networks, Hirshleifer et al. (2025) examined how social

Similarly, rapid advances in ML and AI are creating products and services with the potential not only to change the environment in which actuaries operate but also to provide new opportunities within actuarial science. For example, applications of deep learning to actuarial problems in mortality forecasting (Hainaut, 2018), automobile insurance fraud detection (Ding et al., 2025), life insurance valuation (Noll, 2020), automated machine learning in insurance (Fond & Quan, 2025), claim frequency modeling (Meng et al., 2022), analysis of telematics data (Wüthrich, 2017), and individual claims reserving (Wüthrich, 2018) are remarkable.

Additionally, the actuarial profession is increasingly engaging with climate-related risks and sustainability considerations, using data science to model extreme weather events, assess long-term climate impacts on insurance portfolios, and develop parametric insurance products for climate risks.

The Special Issue aims to further advance the field by inviting original research that:

• Applies innovative data science methods to address challenges in quantitative and sustainable finance, and actuarial science
• Demonstrates empirical robustness and theoretical insight
• Offers practical implications for analysts, insurers, investors, and policymakers

Submissions may employ theoretical models, simulations, or empirical studies and should focus on topics including, but not limited to:

• Machine learning for asset pricing and portfolio optimization
• Market microstructure with data science
• Machine learning for derivatives pricing and hedging
• Analyses of FinTech and InsurTech markets
• Big data in risk management
• Risk modeling with big data and machine learning
• Predictive modeling in actuarial science
• AI and blockchain in sustainable finance
• Climate risk modeling and green finance
• AI-driven ESG factor integration in portfolio management
• Machine learning for carbon market analysis and pricing
• Natural language processing for ESG disclosure analysis
• Transition risk modeling for climate-sensitive sectors
• Machine learning approaches to sustainable supply chain finance
• Data-driven approaches to impact investing and blended finance
• Regulatory technology (RegTech) for sustainability compliance
• Satellite imagery and IoT data for environmental risk assessment

Important deadlines:

• Submission deadline: 31 January 2026

Submission instructions: Please read the [Guide for Authors] before submitting. All articles should be [submitted online], please select [VSI: Data Science] on submission.

Guest editors:

• Yi Cao, Xi’an Jiaotong-Liverpool University, China. Email: yi.cao@xjtlu.edu.cn
• Zhenyu Lu, Xi’an Jiaotong-Liverpool University, China. Email: zhenyu.lu@xjtlu.edu.cn
• Angelos Stefanidis, Xi’an Jiaotong-Liverpool University, China. Email: Angelos.Stefanidis@xjtlu.edu.cn
• Yishuang Xu, University of Manchester, UK. Email: yishuang.xu@manchester.ac.uk