Early Warning Systems in Finance: Anticipating Risk Before Crisis
Armin Sadighi
Ph.D. Candidate at University of Twente
In the rapidly evolving landscape of digital finance, financial institutions are increasingly adopting advanced technologies such as machine learning (ML) to enhance decision-making and risk management. Early warning systems (EWS) are a key component of this shift, helping identify potential financial risks before they escalate into crises. By monitoring credit conditions, market volatility, and macroeconomic trends, EWS provide critical insights into emerging threats. The ability to predict financial risks and respond proactively is essential in today’s fast-paced financial environment. As technology continues to advance, these systems are becoming ever more vital for ensuring financial stability and resilience.
Armin Sadighi is a doctoral candidate at the University of Twente, specializing in the application of machine learning in digital finance as part of the Marie Skłodowska-Curie Actions (MSCA) Doctoral Network. He holds a Master’s degree in Management as well as a Master's degree in Electrical Engineering from the Technical University of Munich and a Bachelor's degree from Amirkabir University of Technology in Computer Engineering. Prior to his PhD, Armin gained industry experience at Allianz and some research experience working in the integrated systems laboratory at Technical University of Munich.
A multi-objective, multi-criteria decision-making approach for a sustainable vaccine supply chain
Yasamin Babaei
Ph.D. Candidate at University of Twente
Vaccines play a vital role in monitoring and preventing the growth of contagious diseases. As of December 2019, with the prevalence of coronavirus worldwide, all communities, particularly developing countries, came across irresistible challenges in vaccines for citizens. Moreover, accurate waste control is of great importance, particularly in the context of infectious medical waste. To address these difficulties regarding vaccine inventory ordering and waste management, this research develops a sustainable multi-objective mixed-integer non-linear programming (MINLP) formulation. To examine real goals, three objective functions are evaluated using a multi-criteria decision-making approach (MCDM). Besides, to explore the applicability of the proposed network, a real case study in one of the central cities in Iran, Kashan province, is considered. According to one of the sensitivity analysis results, extending the review period will be conducive to proliferation in the amount of order quantity and, subsequently, imposing more costs on the chain at a particular time and getting the opportunity from countries to capitalize monetary values in other public affairs.
Yasamin Babaei is a Ph.D. candidate in the Industrial Engineering & Business Information Systems (IEBIS) Section at the University of Twente. She obtained her master’s degree in industrial engineering with a focus on systems optimization from the University of Tehran. Her PhD project is grounded in healthcare, specifically focusing on integral mobility and capacity planning in home healthcare. Her current research interests mainly lie in integrating machine learning techniques and operations research approaches to develop efficient solutions for real-world challenges in the healthcare domain.