1 Objective

Prepare Economists to apply Data Science tools. The extension will help students to develop high-level skills in Data Science, Business, and Computer Science, as illustrated in Figure 1.1. The prospective student are supposed to have a solid background in Math, Statistics and Scientific Methodology.

Data Science must-have skills.

Figure 1.1: Data Science must-have skills.

2 The Graduate

We expect the graduate to be ready to deploy Data Science models and lead technical teams to execute and formulate business strategies based on data. The graduates will criticize data and models with sound economics and analytical fundaments. The solid quantitative background is already a differential of FGV EPGE courses.

3 Networking

Throughout the classes, professionals and entrepreneurs will talk about the strategic use of data in their businesses. Additionally, students will have the opportunity to establish relationships with these professionals in these meetings.

4 Projects

Since the beginning of the extension, we will encourage each student to choose professional projects to develop Machine Learning methods. The Data Science applications are supposed to use Economics and Finance concepts in Portfolio Management, Credit and Churn analysis, Marketing, Insurance, or in other field were Economics may apply.

5 Performance Evaluations

The projects will be the performance assessment of all disciplines with Lab classes. In the Data-Based Business Strategy discipline, students will prepare presentations based on the bibliography suggested by invited professionals.

6 Disciplines

6.1 Data-Driven Business Strategy

Lectures: Genaro Lins e Rafael Martins de Souza

Instructional Hours: 45

Learning Objectives: Develop students’ leadership, communication, business vision, entrepreneurship, and innovation skills.

Methodology: Interaction with outstanding professionals and entrepreneurs. Business readings and debates.

Topics:

  • Soft skills necessary for successful application of Data Science in business: Leadership, Entrepreneurship, Communication, Business Vision, and Innovation.

References:

  • Appointed by the guests during the seminars.

6.2 Introduction to Python for Data Science

Lecturer: Not defined yet.

Instructional Hours: 45

Learning Objectives: Provide programming skills for Data Science.

Methods: Lab classes.

Topics:

  • Case studies of Data Science applied to Economics;

  • Syntax and semantics of the language;

  • Data structures in Python;

  • Objects: Variables and Functions (methods);

  • Operators and related methods;

  • Boolean types;

  • Functional programming;

  • Linear Algebra and matrix manipulation with Numpy;

  • Databases manipulation with Pandas;

  • Data visualization with MatplotLib, Plotly and Altair.

Basic Reference:

  • McKinney, W. Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython (English Edition), 2nd, O’Reilly Media, 2017.

Complementary references:

  • Consoli, S., Recupero, , D. R., Saisana, M. (Ed.), Data Science for Economics and Finance Methodologies and Applications, Springer, 2021.

  • Athey, S., The Impact of Machine Learning on Economics, The Economics of Artificial Intelligence: An Agend, University of Chicago Press, May 2019.

  • Gogas, P., Papadimitriou, T. Machine Learning in Economics and Finance. Comput Econ 57, 1–4, 2021. Disponível em https://doi.org/10.1007/s10614-021-10094-w.

6.3 Machine Learning Applied to Economics

Lecturer: Rafael Martins de Souza

Instructional Hours: 45 hours

Learning Objectives: Allow students to be proficient in implementing Machine Learning models.

Methods: Explanatory and Lab classes.

Topics:

  • The Machine Learning Scenario and its Applications in Economics;

  • End-to-End Machine Learning Project;

  • The Ordinary Least Squares (OLS) and The Gradient Descent;

  • Classification;

  • Model training;

  • Suport Vector Machines;

  • Decison tree;

  • Emsemble and Rando Forests;

  • Dimension Reduction;

  • Unsupervised learning.

Basic Reference:

  • Gueron, A., Hands-On Machine Learning with Scikit-Learn, Keras, and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent Systems, O’Reilly Media; 2nd ed., October 2019.

Complementary references:

  • Consoli, S., Recupero, D. R., Saisana, M. (Ed.), Data Science for Economics and Finance Methodologies and Applications, Springer, 2021.

  • Fasolo, A. M., Graminho, F. M., Bastos, S. B., Seeing the Forest for the Trees: Using hLDA Models to Evaluate Communication in Banco Central do Brasil, Working Paper Series 555, Banco Central do Brasil, August 2021.

6.4 Deep Learning (DL) and Artificial Inteligence (AI) Applied to Economics

Lecturer: Renato Rocha

Instructional hours: 45

Learning Objectives: Allow students to be proficient in implementing Deep Learning and Artificial Intelligence models.

Methods: Explanatory and Lab classes.

Topics:

  • Introduction to Neural Networks (NN) and Deep Learning (DL);

  • Python Packages for NN and DL (Tensor Flow, Keras and Pytorch);

  • Convolucional NN (CNN);

  • Recurent NN (RNN), Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU);

  • Time Series and Natural Language Process with CNN, RNN, LSTM and GRU;

  • Portfolio optimization and financial assert trading with Reinforcement Learning (RL);

  • Generative Models;

  • Autoencoders;

  • GANs;

  • Graph Convolutional Neural Networks;

  • Models deployment and Docker.

Main reference:

  • Gueron, A., Hands-On Machine Learning with Scikit-Learn, Keras, and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent Systems, O’Reilly Media; 2nd ed., October 2019.

Reference on Economics:

  • Consoli, S., Recupero, D. R., Saisana, M. (Ed.), Data Science for Economics and Finance Methodologies and Applications, Springer, 2021.

  • Henderson, J. Vernon, Adam Storeygard, and David N. Weil. 2012. “Measuring Economic Growth from Outer Space.” American Economic Review, 102 (2): 994-1028.DOI: 10.1257/aer.102.2.994, <Measuring Economic Growth from Outer Space - American Economic Association (aeaweb.org) >.

  • Donaldson, Dave, and Adam Storeygard. 2016. “The View from Above: Applications of Satellite Data in Economics.” Journal of Economic Perspectives, 30, 4. The View from Above: Applications of Satellite Data in Economics - American Economic Association.

  • Hoberg, G., Maksimovic, V., Redefining Financial Constraints: A Text-Based Analysis, The Review of Financial Studies, Volume 28, Issue 5, May 2015, Pages 1312–1352, https://doi.org/10.1093/rfs/hhu089.

  • Hansen, S., McMahon, M., Shocking language: Understanding the macroeconomic effects of central bank communication, Journal of International Economics, Volume 99, Supplement 1, 2016, Pages S114-S133, ISSN 0022-1996, https://doi.org/10.1016/j.jinteco.2015.12.008.

  • Hansen, S., Mcmahon, M., Prat, A., transparency And Deliberation Within The Fomc: A Computational Linguistics Approach, The Quarterly Journal of Economics (2018), 801–870.

  • Gentzkow, M., Kelly, B., Taddy, M., Journal of Economic Literature 2019, 57(3), 535–574,https://doi.org/10.1257/jel.20181020.

  • Algaba, A., Ardia, D., Bluteau, K., Borms, S. and Boudt, K. (2020), Econometrics Meets Sentiment: An Overview of Methodology and Applications, Journal of Economic Surveys, 34: 512-547, https://doi.org/10.1111/joes.12370.

  • Taddy, M. (2019). Business data science: Combining machine learning and economics to optimize, automate, and accelerate business decisions. McGraw Hill Professional.

  • Goodfellow, I., Bengio, Y., Courville, A. (2016). Deep learning. Adaptive Computation and Machine Learning. Cambridge, MA: MIT Press (ISBN 978-0-262-03561-3/hbk; 978-0-262-33743-4/ebook). xxii, 775 p. 

  • Deng, Y., Bao, F., Kong, Y., Ren, Z., Dai, Q. (2017), “Deep Direct Reinforcement Learning for Financial Signal Representation and Trading,” in IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 3, pp. 653-664, March 2017, doi: 10.1109/TNNLS.2016.2522401.

6.5 Information Tecnology for Data Science

Lecturer: Júlio César Chaves

Instructional hours: 45

Learning Objectives: Provide the students with the Information Technology (IT) knowledge necessary to lead and interact with IT staff at a high level with professionals in the field and lead Data Science teams.

Methods: Explanatory and Lab classes.

Topics:

  • Entity-Relationship Model.

  • Entity types, entity sets and key attributes.

  • Types of relationships, roles and structural constraints.

  • Entity-Relationship Diagram.

  • Relational Data Model. Key attributes of a relationship.

  • Relational Database Schemes and Integrity Constraints.

  • Formal Query Languages: Relational Algebra.

  • The SQL language. NoSQL Databases. RDF Databases.

  • Gremilin and SQL analytic functions.

  • Data Formats. Dimensional Modeling and Data Models.

  • Structured Data and Unstructured Data.

  • Extraction, Transformation and Loading (ETL and ELT).

  • Streaming data. Data Warehouse and Data Lake projects.

  • Systems and Best Practices for Big Data Management.

  • Data Management and Governance and GDPR.

References:

  • Jukic, N., Vrbsky, S., Nestorov, S., & Sharma, A. (2021). Database Systems: An Introduction to Databases and Data Warehouses.

  • David Hay. Data Model Patterns: a metadata map. Morgan Kaufmann, 2006.

  • Kimball, R., & Ross, M. (2013). The Data Warehouse Toolkit: The Definitive Guide to Dimensional Modeling, 3rd ed.; I. John Wiley & Sons.

  • Sharma, B. (2018). Architecting Data Lakes. O’Reilly Media, Inc. http://www.oreilly.com/data/free/architecting-data-lakes.csp.

  • Bill Inmom. Data Lake Architecture: Designing the Data Lake and Avoiding the Garbage Dump.

  • Rêgo, B. L. (2013). Gestao e Governanca de Dados: Promovendo Dados Como Ativo de Valor nas Empresas, S. M. de Oliveira, ed. 

  • Seidl, M., Scholz, M., Huemer, C., & Kappel, G. (2015). UML @ classroom : an introduction to object-oriented modeling. Springer International Publishing.