
Contact
4032 Business Instructional Facility
515 Gregory Dr
Champaign, IL 61820
Listings
Educational Background
- Ph.D., Finance, Massachusetts Institute of Technology at Cambridge, 2018
- M.A., Economics, Getulio Vargas Foundation (EPGE-FGV) at Rio de Janeiro, 2012
- B.Eng., Aeronautical Engineering, Aeronautical Institute of Technology (ITA) at São José dos Campos,, 2009
Positions Held
- Assistant Professor of Finance, University of Illinois at Urbana-Champaign, 2019 to present
Recent Publications
- Duarte, V. Forthcoming. Compounding Money and Nominal-Price Illusions. Management Science.
- Duarte, V. Forthcoming. Machine Learning for Continuous Time Finance. Review of Financial Studies.
Other Publications
Working Papers
- Duarte, V., Kargar, M., Li, J., & Silva, D. Dissecting the Aggregate Market Elasticity.
- Duarte, V., Fonseca, J., Goodman, A., & Parker, J. Simple Allocation Rules and Optimal Portfolio Choice Over the Lifecycle.
Current Courses
-
Introduction to ML in Finance (FIN 453) Machine Learning includes the design and the study of algorithms that can learn from experience, improve their performance, and make predictions. In this course, students will learn the foundations of Machine Learning and explore standard tools and algorithms. Topics include supervised learning (neural networks, regression trees, gradient boosting), unsupervised learning (clustering, principal component analysis), and introduction to reinforcement learning (Deep Q-Networks). Applications include option pricing, and credit card fraud detection. Students will gain practical experience implementing these models in Python with frequently used packages such as PyTorch, ScikitLearn and XGBoost.
-
Machine Learning in Finance (FIN 553) Machine Learning includes the design and the study of algorithms that can learn from experience, improve their performance and make predictions. In this course students will learn the foundations of Machine Learning and explore state of the art algorithms and tools. Topics include supervised learning (neural networks, support vector machines), unsupervised learning (clustering, dimensionality reduction) and reinforcement learning (dynamic programming, Q-learning, SARSA, policy gradient methods). Applications include option pricing, portfolio selection and credit card fraud detection. Students will gain practical experience implementing these models in Python with frequently used packages such as TensorFlow.
Contact
4032 Business Instructional Facility
515 Gregory Dr
Champaign, IL 61820