Erik Cambria is a Professor of Artificial Intelligence at NTU CCDS, where he also holds the appointment of Provost Chair in Computer Science and Engineering, and a Visiting Professor at MIT Media Lab. He has founded several AI companies, such as SenticNet (https://business.sentic.net), offering B2B sentiment analysis services, and finaXai (https://finaxai.com), providing fully explainable financial insights, and has worked at HP Labs and Microsoft Research prior to joining academia. Today, his research focuses on neurosymbolic AI for interpretable and explainable affective computing in domains like mental health, climate resilience, and socially responsible investing. Prof Cambria is ranked in Clarivate's Highly Cited Researchers List of World's Top 1% Scientists, is recipient of many awards, e.g., IEEE Outstanding Early Career, was listed among the AI's 10 to Watch, and was featured in Forbes as one of the 5 People Building Our AI Future. He is an IEEE Fellow, Associate Editor of various top-tier AI journals, e.g., Information Fusion and IEEE Transactions on Affective Computing, and is involved in several international conferences as keynote speaker, program chair and committee member.

Talk Title: From Public Opinion to Market Movements: Explainable NLP for Strategic Financial Insights

Recent advances in LLMs are transforming how we understand the interplay between language, public opinion, and financial decision-making. This talk presents a series of works that integrate affective computing, explainable AI, and financial NLP to derive actionable insights for both market strategy and risk management. We first introduce methods for forward counterfactual generation, enabling strategic market foresight through scenario modeling with LLMs. We then examine how social media mining can support public opinion crisis management, highlighting its implications for corporate resilience. Moving from public sentiment to corporate communication, we explore cognitive analyses of CEO speeches and their measurable effects on stock markets. In the trading domain, we discuss how top-down sector allocation can be automated with LLMs, and how explainable NLP techniques support transparent assessments of corporate sustainability. Finally, we show how contrastive learning enhances interpretability in stock price movement prediction. Together, these contributions outline a neurosymbolic and explainable approach to financial AI—one that emphasizes transparency, robustness, and trustworthiness in high-stakes decision-making.

Chung-Chi Chen is a researcher at the Artificial Intelligence Research Center, AIST, Japan, focusing on financial opinion mining and the understanding/generation of financial documents. 

Talk Title: Human-Centric Evaluation for Financial Decision-Making

In the era of Human-AI collaboration, evaluating LLMs based solely on accuracy and efficiency is no longer sufficient. This talk explores decision-oriented evaluation, a human-centric approach that measures how AI-generated analyses influence real-world decision quality. Using financial decision-making as a case study, we demonstrate that while models like GPT-4 can produce persuasive analytical texts, they may not necessarily lead to better human decisions—and may even mislead experts under certain conditions. Through a series of studies, we examine how human expertise, trust, and persuasion interact with model-generated content, and propose a framework for Human-Agent Teaming that integrates expert insight with AI-driven analysis. By shifting evaluation from text similarity to decision outcomes, this research aims to redefine how we measure model effectiveness in high-stakes domains such as finance, healthcare, and policy analysis. 

Director – Senior Research Advisor, Directorate General for Information Technology, Bank of Italy

Claudia Biancotti joined Banca d’Italia in 2002. She currently serves as Senior Research Advisor in the Directorate General for Information Technology, working at the intersection of economics and computer science research. She is interested in how digitalization is changing the economy and society, with a focus on security implications. Her latest work focuses on AI alignment, the rise of decentralized systems and cryptoassets, and cybersecurity. Claudia was a visiting fellow at the Peterson Institute for International Economics in Washington, DC in 2018-2019, and a seconded national expert at the European Central Bank in 2009-2010.

Manager, AI Foundations - AI Center of Excellence (AI COE), Mastercard

Tech lead with over a decade of experience in software engineering, data engineering, and machine learning. At Mastercard, he drives innovation in AI governance and machine learning pipelines, leading the development of bias testing and mitigation tools across private and public cloud environments.

Research Associate in the Computational Logic and Argumentation Group, Department of Computing, Imperial College London.