cv

Research Assistant to Prof. Tarek Hassan

Boston University

Pre-Doctoral Fellow (Prof. Michael Best)

Columbia University

Pre-Doctoral Fellow (Prof. Réka Juhász)

Columbia University

Research Assistant to Prof. Juan Sebastián Galán

Universidad de los Andes

Teaching Fellow — Introduction to Microeconomics

Boston University

TF to Prof. Onur Celik (Fall) and Prof. Todd Idson (Spring).

Teaching Assistant — Global Economic History

Universidad de los Andes

TA to Prof. Juan Sebastián Galán.

Teaching Fellow — Introduction to Econometrics

Universidad de los Andes

TF to Prof. Ramón Rosales.

Teaching Fellow — Introduction to Microeconomics

Universidad de los Andes

TF to Prof. Juan Camilo Cárdenas and Prof. Andrés Moya.

PhD (Expected 2028)

Boston University

Economics

MA

Universidad de los Andes

Economics

• Advanced Econometrics
• Advanced Microeconomics General Equilibrium
• Forecasting in Economics

BSc

Universidad de los Andes

Economics

Best results in the State examinations for higher education quality (SABER PRO)

Colombian Ministry of Education

Andrés Bello distinction for best results in the high school exit examination (SABER 11)

Colombian Ministry of Education

Localization and Steering of Economic Uncertainty in Large Language Models.

Working Paper

Economic uncertainty shapes investment, hiring, and asset prices, making its measurement from text a central task in economics and finance. While LLMs accurately measure uncertainty in financial texts such as earnings call transcripts, it remains unclear whether they develop coherent internal representations or merely pattern-match on surface lexical cues. In this study, we discover that LLMs linearly represent economic uncertainty with a single direction in the residual stream. Using activation patching on two synthetic datasets of contrastive earnings-call statements with varying linguistic styles, we localize this direction and find that models aggregate the uncertainty signal at the final token regardless of lexical patterns. The extracted direction perfectly separates held-out high- and low-uncertainty statements both within- and cross-dataset. Causal interventions show that adding or subtracting this direction monotonically flips uncertainty predictions, including cross-dataset transfer from templated to naturalistic text. Finally, in a downstream portfolio allocation task using real earnings-call excerpts, steering along the uncertainty direction shifts model investment toward safe assets, consistent with economic theory. Together, our results establish that LLMs encode economic uncertainty as a structured, causally active, and transferable representation, offering a foundation for interpretability-based auditing and control of LLMs deployed in financial analysis.

Measuring Industrial Policy: A Text-Based Approach.

Working Paper

Since the 18th century, policymakers have debated the merits of industrial policy (IP). Yet, economists lack basic facts about its use due to measurement challenges. We propose a new approach to IP measurement based on information contained in policy text. We show how off-the-shelf supervised machine learning tools can be used to categorize industrial policies at scale. Using this approach, we validate longstanding concerns with earlier approaches to measurement which conflate IP with other types of policy. We apply our methodology to a global database of commercial policy descriptions, and provide a first look at IP use at the country, industry, and year levels (2010-2022). The new data on IP suggest that i) IP is on the rise; ii) modern IP tends to use subsidies and export promotion measures as opposed to tariffs; iii) rich countries heavily dominate IP use; iv) IP tends to target sectors with an established comparative advantage, particularly in high-income countries.

The effect of industrialization on political dynasties: Evidence from Colombian local governments.

M.A. Thesis

In this paper I find that industrialization reduces the concentration of political power, measured by the share of elected officials that were part of political dynasties, in the context of 19 Colombian departments. I use newly digitized data from departmental production by industrial sector since 1969 and the international price of manufactures as an exogenous source of variation in the industrialization levels. Using an instrumental variable approach, I find that an increase in one paid manufacturing employee reduces the share of elected individuals from dynasties by 1.15 p.p. Dividing the results by type of office indicates that the impact is more prominent in the election of dynastic individuals in the legislative brand compared to those elected in the executive one. One additional paid employee decreases the average share of dynastic mayors by 0.75 p.p., a 7.8% decrease in the average. On the other hand, an increase in a paid employee decreases the percentage of representatives from dynastic families by 3.24 p.p., which represents a diminution of 13.4%.