AI-based Dynamic Return and Sustainability Factor Timing for Equity Mutual Funds
Project Description
This project proposes a novel approach to factor investing, tailored to LLB Asset Management AG's long-only equity investment universe. The innovation focuses on dynamically timing a wide range of return factors, including traditional elements like size, value or momentum, and sustainability factors such as the green-minus-brown factor based on carbon footprints of companies.
Leveraging cutting-edge machine learning and AI technologies, we aim to develop a precise factor timing framework. The project is divided into three work packages. The first focuses on developing an advanced factor-timing strategy, employing state-of-the-art analytical tools for long-only equity factors. The second package addresses sustainability aspects, applying traditional factor timing concepts on sustainability-related factors to optimize market-timing signals while simultaneously keeping the portfolio above certain standards. The third package aims to calibrate and dynamically adjust factor weightings in a multi-factor long-only sustainable investment approach, optimizing portfolio characteristics.
Our team, comprising experts from LLB Asset Management AG and the University of Liechtenstein, brings together a blend of practical and academic expertise in factor investing, machine learning, and ESG investing. The project aspires to enhance LLB’s long-only equity fund performance while achieving a positive impact on the society and environment by purposefully channeling funds to sustainable investment opportunities. Findings shall also be shared through academic journals and conferences gaining peer-feedback and underscoring the project's innovative contribution in shaping sophisticated investment strategies responsive to market dynamics and sustainability considerations.
Leveraging cutting-edge machine learning and AI technologies, we aim to develop a precise factor timing framework. The project is divided into three work packages. The first focuses on developing an advanced factor-timing strategy, employing state-of-the-art analytical tools for long-only equity factors. The second package addresses sustainability aspects, applying traditional factor timing concepts on sustainability-related factors to optimize market-timing signals while simultaneously keeping the portfolio above certain standards. The third package aims to calibrate and dynamically adjust factor weightings in a multi-factor long-only sustainable investment approach, optimizing portfolio characteristics.
Our team, comprising experts from LLB Asset Management AG and the University of Liechtenstein, brings together a blend of practical and academic expertise in factor investing, machine learning, and ESG investing. The project aspires to enhance LLB’s long-only equity fund performance while achieving a positive impact on the society and environment by purposefully channeling funds to sustainable investment opportunities. Findings shall also be shared through academic journals and conferences gaining peer-feedback and underscoring the project's innovative contribution in shaping sophisticated investment strategies responsive to market dynamics and sustainability considerations.
