I’m an applied microeconomist with over five years of experience in causal inference research and broad expertise in data analytics, machine learning, stochastic simulations, and large-scale data handling. I also have over three years of hands-on experience developing deep-learning models and hyperparameter tuning.
My research centers on understanding firms’ decision-making processes by integrating applied microeconometric techniques with cutting-edge machine learning and deep learning methods.
My expected graduation date is July 2025. I will be available for interviews in the 2024-2025 job market.
Working Papers
-
National Firms, Local Effects: Spillovers from Multi-Establishment Employers' Expansion
Job Market Paper.
[abstract]
Abstract: This paper examines how the expansion of large, multi-establishment (national) employers influences the wage and hiring policies of smaller, local firms. Although these expansions are firms' independent decisions, understanding their spillover effects is important for evaluating policies that aim to attract new large employers. Using administrative data from Brazil that cover firms' wages and employment across different locations and occupations, I conduct a matched event study to assess how local employers respond to significant, idiosyncratic labor demand shifts by national employers. The findings reveal that when national employers increase wages in large cities by 8 log points (relative to other employers in large cities), they simultaneously raise wages by 5 log points and expand employment in other locations. This expansion pressures local employers to increase wages by 2 log points, resulting in a 1.5 log point wage growth for incumbent workers. Despite local employers reducing employment, workers are not adversely affected because they reallocate to the expanding national employers. -
Spooky Boundaries at a Distance: Inductive Bias, Dynamic Models, and Behavioral Macro.
with Mahdi Ebrahimi Kahou, Jesus Fernandez-Villaverde, Sebastian Gomez-Cardona and Jesse Perla, Revise and Resubmit, Journal of Monetary Economics
[abstract] [NBER Working Paper]
Abstract: In the long run, we are all dead. Nonetheless, when studying the short-run dynamics of economic models, it is crucial to consider boundary conditions that govern long-run, forward-looking behavior, such as transversality conditions. We demonstrate that machine learning (ML) can automatically satisfy these conditions due to its inherent inductive bias toward finding flat solutions to functional equations. This characteristic enables ML algorithms to solve for transition dynamics, ensuring that long-run boundary conditions are approximately met. ML can even select the correct equilibria in cases of steady-state multiplicity. Additionally, the inductive bias provides a foundation for modeling forward-looking behavioral agents with self-consistent expectations.
Work in Progress
-
Heterogeneous Firm Sorting and Local Monopsony Power
with Xiaojun Guan and Sudipta Ghosh
[abstract]
Abstract: This paper examines firm-related sources of urban wage premium. Specifically, we study the roles of (1) more productive firms sorting to larger labor markets and (2) the degree of labor market concentration in driving spatial wage inequality. While previous studies have acknowledged the significance of both factors, their interactions have not been quantified. Using the Sample of Integrated Labour Market Biographies (SIAB) from the German Institute for Employment Research (IAB), we first document a series of stylized facts about the spatial distribution of firms’ labor market power, wage policies, industry compositions, and firm sizes. Next, motivated by the stylized facts, we develop a spatial general equilibrium model that integrates location choices of heterogeneous (discrete type) firms and oligopsonistic local labor markets. In the model, we assume sequential entry of firms with high-productivity type firms deciding where to enter first, followed by low-productivity types. Larger labor markets are endowed with more productive workers. Hence, firms face a trade-off: while entering larger labor markets can lead to higher output, it also results in increased competition for labor, thereby raising labor costs. The relative strength of these opposing forces determines the equilibrium spatial distributions of firms and wages. Finally, we calibrate our model using two administrative datasets from Germany—the employer-employee sample and the establishment panel—to quantify the relative impact of firm sorting and labor market concentration on spatial wage inequality and conduct policy counterfactual experiments.