1. ALIENs and Continuous Time Economies
Presentations: Princeton University (2022), SFI-UZH Computational Finance seminar (2021), EUI Artificial Intelligence seminar (2021).
: I develop a new computational framework called Actively Learned and Informed Equilibrium Nets (ALIENs) to solve continuous time economic models with endogenous state variables and highly non-linear policy functions. I employ neural networks that are trained to solve supervised learning problems that respect the laws governed by the economic system in the form of general parabolic partial differential equations. The economic information is encoded as regularizers that disciplines the deep neural network in the learning process. The sub-domain of the high dimensional state space that carries the most economic information is learned actively in an iterative loop, enforcing the random training points to be sampled from areas that matter the most to ensure convergence. I utilize a state-of-the art distributed framework to train the network that speeds up computation time significantly. The method is applied to successfully solve a model of macro-finance that is notoriously difficult to handle using traditional finite difference schemes.
2. Intermediaries with something to lose: On the origins and consequences of bank failures (Draft available upon request)
Presentations: 20th Macro Finance Society PhD session (2022), CESifo Conference on Macro, Money, and International Finance (2022), EPFL-UNIL PhD seminar (2022), SFI-UZH Computational Finance seminar (2022).
: This paper builds a macro-finance model with endogenous bankruptcy of intermediaries to analyze the dynamics of financial crises. The model features leveraged intermediaries who face stochastic costs to intermediate assets, and possess franchise value that they lose upon bankruptcy, trapping the economy in states of economic distress with slow recovery. The model quantitatively predicts a large risk premium, low GDP growth, and high bank failures during financial crisis. Analyzing a panel of Bank Holding Companies, I offer empirical evidence for the franchise value to be associated with a higher probability of failure. The results indicate that the changing scope of banking industry with declining franchise value compared to the pre-crisis period is worrisome, despite strong capital ratios.
Work in Progress
3. Capital Structure Dynamics with Active Debt and Equity Management with Julien Hugonnier and Erwan Morellec
4. Interest Rate Uncertainty and Public Debt Dynamics with Andrea Modena
5. Supply Chain Finance and Firm Capital Structure with Claudio Tebaldi and Laura Bottazzi (Draft available upon request)