Recommender Systems in Finance (Fin-RecSys) 

Recommender systems are rapidly emerging as crucial tools in the financial sector, aiding a spectrum of financial agents from retail investors to regulators. A notable survey highlighted that 23% of financial services professionals are adopting AI-driven recommender systems, underscoring the sector's growing reliance on such technologies to enhance decision-making and asset management. This workshop aims to delve into the development and application of advanced machine learning and optimization models tailored for financial recommender systems, spanning a range of users and items including stocks, bonds, loans, and real estate.

The workshop will explore innovative methodologies like collaborative filtering, portfolio optimization, and reinforcement learning, alongside cutting-edge Large Language Models (LLMs). Key themes include personalized recommendations, investor modeling, and the explainability and ethics of investment suggestions. With financial markets' volatility, the challenge lies in aligning recommendations with client preferences while ensuring optimal investment outcomes, necessitating sophisticated investor modeling and asset similarity learning techniques.

This gathering will serve as a bridge between academia and industry, addressing critical gaps such as inconsistent evaluation criteria and the need for synthetic datasets to navigate privacy concerns. Building on previous workshops, this session aims to push the frontier of quantitative behavioral finance by fostering dialogue on state-of-the-art research in financial recommender systems. Participants are encouraged to contribute to a special issue on “Statistical and Machine Learning for Investor Modeling” at the Journal of Behavioral Finance, which is guest edited by three of the co-organizers.