During the project, you will closely collaborate with industry and a doctoral training network spread throughout Europe, including extended research stays abroad.
The successful applicant will join the Industrial Engineering and Business Information Systems (IEBIS) section of the High-tech Business & Entrepreneurship Department (HBE) at the Faculty of Behavioural Management and Social Sciences (BMS).
Background This Ph.D. position is one of four positions at the University of Twente in the context of the international Marie Sklodowska-Curie Actions project DIGITAL. For the general description of DIGITAL and the Ph.D. positions, please check https://euraxess.ec.europa.eu/jobs/178873
DIGITAL' main goal? To significantly advance the methodologies and business models for Digital Finance through the use of five interconnected research objectives https://www.digital-finance-msca.com/:
- Ensure sufficient data quality to contribute to the EU's efforts of building a single digital market for data;
- Address deployment issues of complex artificial intelligence models for real-world financial problems;
- Validate the utility of state-of-the-art explainable artificial intelligence (XAI) algorithms to financial applications and extend existing frameworks;
- Design risk management tools concerning the applications of Blockchain technology in Finance;
- Simulate financial markets and evaluate products with a sustainability component.
This project closely relates to objectives 1, 2, 3, and 5, as we aim to provide a recommender system that improves data quality, applies sophisticated AI technologies to real-world financial scenarios, incorporates explainable AI to increase transparency and trust, and supports the simulation and evaluation of sustainable financial products. Through this, we contribute to the development of a digital single market for data within the EU, aligned with sustainable finance principles.
Recommender systems are well-known information filtering systems that suggest items most relevant to a user. Although recommender systems have been successful in many domains, there are presently none that suggest appropriate investments in sustainable technologies and businesses. This project will develop and deploy a recommender system to inform financial institutions and their clients about investments' sustainability and help to invest in sustainable businesses.
Modern recommender systems are generally a hybrid of content-based and collaborative-based filters through sophisticated algorithmic pipelines, using both item information and user information to get the best out of both worlds. In the financial domain, a key challenge for such hybrid architectures is to ensure regulatory compliance and eliminate potential bias.
The main objective of this research project is to develop a recommender system that applies filters based on both stock data and investor data to offer relevant, diversified, and targeted recommendations that will help propel sustainable investments. In doing so, it is imperative that the system follows regulations and prevents undesirable biases.