Call for Expressions of Interest – Marie Skłodowska-Curie Postdoctoral Fellowships

The University of Verona is among the top hundred world universities with less than 50 years in the rankings of Times Higher Education (Young University Rankings 2024). In the RepEc ranking, the Department of Economics ranks in the top 10% of the Italian distribution (https://ideas.repec.org/top/top.italy.html). It received the “Department of Excellence 2023-2027” seal by the Italian ministry of university and research.

For more information on the fellowship and eligibility, please visit the official Marie Curie Fellowships page.

Interested candidates are invited to email a brief outline of their research proposal and their CV to ricerca@dse.univr.it by 25 June 2025.

Econometrics

Supervisor: Giuseppe Buccheri

Title of the project: A New Paradigm for Dynamic Network Modeling

Description:

This research agenda develops innovative econometric methodologies to infer the structure and evolution of dynamic networks, with applications in financial markets, macroeconomics, and systemic risk. The project builds on the recently introduced Realized Random Graphs (RRGs) technique, that transforms complex, nonlinear network models into linear time-series models, enabling scalable estimation and inference in high-dimensional environments.

The research addresses several key dimensions:

1. Theoretical development of inference methods for sparse networks, including the use of regularization techniques like LASSO to ensure consistency in low-density regimes.

2. Community detection exploiting dynamic information, capturing how groups of agents co-evolve in response to economic or financial shocks.

3. Systemic risk monitoring, stress-testing, and scenario analysis based on reduced-form representations of large financial networks.

This line of research connects econometrics, network science, and quantitative finance. It aims to equip institutions and policymakers with flexible tools for real-time monitoring and risk management in increasingly interconnected economic systems.

 

Economic Policy

Supervisor: Angelo Zago

Title of the project: Internationalization and global sourcing in an era of uncertainty

Description:

The undergoing research project is analyzing Foreign Direct Investment (FDI) and Global Value Chains (GVC), investigating questions like the following:

1. Are inward FDI useful for the local economy? If so, how is it possible to attract foreign capital? How can they be retained? For outward FDI, what are their effects (in terms of employment and investments) on the local economy?

These themes and other related questions are being explored through econometric analysis of cross-border mergers and acquisitions with firm-level data, also using information on financial statements, employment contracts and international trade.

2. Global Value Chains and Global Sourcing. What do we know about subcontracting companies and their relationships with other companies, particularly with the leading companies, both domestic and foreign? What is the position of local companies in the GVCs in which they are included? What are the differences among business networks from different sectors? What are the policies to improve competitiveness of these GVC?

 

Statistics

Supervisor: Catia Scricciolo 

Title of the project: Machine Learning Techniques for Uncertainty Quantification in Life Sciences 

Description: 

Machine Learning (ML) is revolutionizing scientific activities by leveraging complex models, large-scale datasets, and adaptive algorithms. However, uncertainty arises at various stages, from model predictions and hyperparameter estimation to data quality. Accurately quantifying this uncertainty is critical for robust decision-making and enhancing user trust. Active research focuses on uncertainty representation and model calibration, particularly for complex data like text, images, etc. These advances are driving significant breakthroughs in neuroscience, ecology, cancer biology, and other life sciences.

The proposal aims to address the following aspects:

1. Understanding and developing theoretical inferential methods for Convolutional Neural Networks (CNNs), among which Bayesian Neural Networks (BNNs), using variational inference to ensure efficient, accurate and interpretable predictions.
2. Application to grid-structured data by implementing these methods for image, video or medical scan analysis (e.g., X-rays, MRIs)