Laura Gualda

Laura Gualda is a Research Associate and Ph.D. candidate at the Chair of Transport Systems Engineering at the Technical University of Munich (TUM) under the supervision of Prof. Dr. Constantinos Antoniou since February 2024. Her current research focuses on uncertainty quantification in machine learning frameworks, transfer learning methods for traffic flow estimation and transport-related air pollution.

Prior to her current position as Research Associate, Laura worked for five years in data engineering and analytics in the private sector in Berlin. She holds an M.Sc. in Mathematical Data Modelling from the School of Applied Mathematics of Fundação Getulio Vargas (Rio de Janeiro, Brazil) and a B.Sc. in Economics from the Brazilian School of Economics and Finance of the same institution.

Education and Training

2024 - present

Ph.D. Candidate

Chair of Transportation Systems Engineering

Technical University of Munich (TUM), Munich, Germany

2016 - 2018

M.Sc. Mathematical Data Modelling

Coursework: Data Mining; Multivariate Statistics; Machine Learning; Monte Carlo Simulation Methods

Thesis: Learning about corruption: a statistical framework for working with audit reports
Fundação Getulio Vargas (FGV/EMAp), Rio de Janeiro, Brazil

2012 - 2015

B.Sc. Economics

Focus on Econometrics and Causal Inference
Fundação Getulio Vargas (FGV/EPGE), Rio de Janeiro, Brazil

Work Experience

2024 - present

Research Associate at the Chair of Transportation Systems Engineering, TUM, Munich

Working on the MI-TRAP project

2022 - 2024

Data Engineer at DeepL SE, Berlin

2020 - 2022

Data Engineer at Delivery Hero SE, Berlin

2018 - 2020

Fraud Data Analyst at Fraugster GmbH, Berlin

2017 - 2018

Machine Learning Graduate Intern at IBM Research, Rio de Janeiro, Brazil

2012 - 2017

Research and Teaching Assistant at Fundação Getulio Vargas, Rio de Janeiro, Brazil


Reinaldo Mozart Da Gama e Silva, Laura Gualda, Lucas F. Lima, Emilio A. Vital Brazil, Renato F. G. Cerqueira, Rogério A. Paula and Ulisses T. Mello (2018). Sensitivity Analysis in a Machine Learning Methodology for Reservoir Analogues. Rio Oil & Gas Expo and Conference Proceedings, p. 24-27, 2018.