My research interests are very broad and span from mathematical economics, econometrics, financial mathematics, and environmental economics.
Part of my research work is focused on discrete choice modeling for estimation of preferences and utility functions. I am also interested in research projects in econometrics and high-dimensional statistics.
Finally, I am interested in machine learning applications to improve identification of causal effects in econometric models, reinforcement learning to find solutions for dynamic stochastic general equilibrium models, and deep learning algorithms for portfolio optimization.
Below you can find detailed descriptions of my recent papers. Please do not hesitate to contact me if you have any questions.
Understanding Public Preferences for Molluscan Shellfish Aquaculture: The Role of Production Technology and Ecosystem Services
Giulio Farolfi, Robert J. Johnston - Marine Resource Economics (2024)
Abstract: Molluscan aquaculture is often promoted as an alternative to wild-capture shellfisheries, yet aquaculture expansion is sometimes opposed by groups concerned with aesthetics and use conflicts. Amidst these conflicts, public preferences remain unquantified in rigorous terms. This article presents a novel discrete choice experiment (DCE) designed to elicit preferences for large-scale bivalve aquaculture, focusing on production technology, economic and environmental impacts. Results for a Connecticut (USA) case study show that WTP is heterogeneous, with the largest impacts on preferences due to water clarity impacts, employment gains, and location. We find little evidence of negative preferences for bivalve aquaculture among typical respondents.
In-Context Operator Learning for Linear Propagator Models
Tingwei Meng, Moritz Voss, Nils Detering, Giulio Farolfi, Stanley Osher, Georg Menz (forthcoming, 2025)
Abstract: We study operator learning in the context of linear propagator models for optimal order execution with transient price impact a la Bouchaud et al. (2004) and Gatheral (2010). Transient price impact persists and decays over time according to some propagator kernel. Specifically, we propose to use In-Context Operator Networks (ICON), a novel transformer-based neural network architecture introduced by Yang et al. (2023), which facilitates data-driven learning of operators by merging offline pre-training with an online few-shot prompting inference. First, we train ICON to learn the operator from various propagator models that maps the trading rate to the induced transient price impact. The inference step is then based on in-context prediction, where ICON is presented only with a few examples. We illustrate that ICON is capable of accurately inferring the underlying price impact model from the data prompts, even with propagator kernels not seen in the training data. In a second step, we employ the pre-trained ICON model provided with context as a surrogate operator in solving an optimal order execution problem via a neural network control policy, and demonstrate that the exact optimal execution strategies from Abi Jaber and Neuman (2022) for the models generating the context are correctly retrieved. Our introduced methodology is very general, offering a new approach to solving optimal stochastic control problems with unknown state dynamics, inferred data-efficiently from a limited number of examples by leveraging the few-shot and transfer learning capabilities of transformer networks.