Data Science for Economics and Finance¶

Course Description¶

In this course, students will delve into the cutting-edge applications of Data Science in the domains of economics and finance. Leveraging the Big Data era's vast data pools, the course will teach students to handle, process, link, and analyze data to make impactful economic and financial forecasts. Students will learn machine learning methods, text mining, sentiment analysis, and network analysis as they relate to modern economics and finance.

Learning Goals¶

By the end of this course, students will be able to:

Understand the core principles of Data Science and their applications in economics and finance.
Apply machine learning techniques to real-world economic and financial data.
Utilize text mining to analyze corporate earnings calls, firm disclosures, and financial news.
Leverage new data sources and methodologies for central banks and macroeconomic nowcasting.
Conduct sentiment analysis and narrative quantification to predict market risks.
Explore network analysis within the context of economics and finance, such as firm ownership patterns.

Grading¶

Participation: 10%
Midterm presentation: 20%
Final presentation: 30%
Term Project: 40%

Course Schedule¶

Week 1: Introduction¶

Introduction to Data Science Technologies in Economics and Finance
Overview of Machine Learning Methods

Week 2: Measuring Uncertainty with Text¶

Text Analysis Concepts
Applications to Earnings Conference Calls and Other Firm Disclosures

Week 3: Earnings Conference Calls and Other Firm Disclosures¶

Detailed Analysis and Case Studies

Week 4: New Data Sources for Central Banks 1¶

Data Sources and Their Importance
Practical Applications in Monetary Policy

Week 5: New Data Sources for Central Banks 2¶

Continued Exploration of Data Sources
Applications to Financial Regulations

Week 6: Semi-supervised Text Mining for Monitoring the News About the ESG Performance of Companies 1¶

Introduction to ESG Performance
Semi-supervised Learning Techniques

Week 7: Semi-supervised Text Mining for Monitoring the News About the ESG Performance of Companies 2¶

Advanced Techniques in Text Mining
Practical Implementation

Week 8: Mid-term¶

Midterm Presentation
Review and Reflection on the First Half of the Course

Week 9: Sentiment Analysis of Financial News: Mechanics and Statistics 1¶

Introduction to Sentiment Analysis
Statistical Approaches

Week 10: Sentiment Analysis of Financial News: Mechanics and Statistics 2¶

Advanced Techniques in Sentiment Analysis
Case Studies and Analysis

Week 11: Extraction and Representation of Financial Entities from Text¶

Techniques for Data Extraction
Representation Learning

Week 12: Quantifying News Narratives to Predict Movements in Market Risk¶

Narrative Analysis Techniques
Case Studies in Market Risk Prediction

Week 13: Massive Data Analytics for Macroeconomic Nowcasting¶

Big Data Techniques
Economic Prediction and Nowcasting Applications

Week 14: Network Analysis for Economics and Finance: An Application to Firm Ownership¶

Introduction to Network Analysis
Application to Firm Ownership

Week 15: Final Presentation¶

Final Project Presentations
Conclusion and Future Trends in Data Science for Economics and Finance

Additional Resources¶

Students will have access to various online resources, tutorials, and reading materials to supplement the coursework. Collaboration with peers and engagement with instructors will be strongly encouraged.

Note¶

The syllabus is subject to change, and students will be notified of any modifications in a timely manner. Any updates, assignments, and relevant information will be available through the course platform.