Data Science for Economics and Finance

Description

This course aims to provide students with a comprehensive understanding of data science applications in economics and finance. It will cover the main concepts, evolution, technical challenges, infrastructures, roles, and opportunities offered by data science in these sectors. Students will learn about various machine learning and data analysis techniques applied in economic forecasting, nowcasting, and financial services.

Course Objectives

The primary objectives of this course are to:

1. Introduce students to the fundamentals of data science and its applications in economics and finance.

2. Provide an understanding of the main concepts, methodologies, and tools used in data science for economics and finance.

3. Explore the potential of data science techniques in improving economic forecasting, nowcasting, and financial services.

4. Encourage students to apply data science techniques to real-world economic and financial problems.

5. Foster critical thinking and problem-solving skills in the context of data-driven decision-making.

Learning Outcomes

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

1. Understand the role of data science in economics and finance and its potential for improving forecasting and decision-making processes.

2. Apply various machine learning and data analysis techniques to economic and financial data.

3. Interpret the results of data-driven models and draw meaningful conclusions to inform economic and financial decisions.

4. Analyze and process large-scale datasets using advanced data analytics techniques.

5. Evaluate the effectiveness of different data science methodologies and tools in addressing specific economic and financial challenges.

Textbook

The primary textbook for this course is:

Consoli, S., Recupero, D.R., & Saisana, M. (2021). Data Science for Economics and Finance: Methodologies and Applications. Springer International Publishing. ISBN: 9783030668907. Available Online

This textbook offers a comprehensive overview of data science applications in economics and finance, covering essential concepts, methodologies, and tools. Students are expected to read the assigned chapters and articles from this book to enhance their understanding of the course material.

Prerequisites

Students enrolling in this course should have:

1. A basic understanding of economics and finance concepts.

2. Familiarity with fundamental statistical concepts and methods.

3. Proficiency in programming, preferably in Python.

4. Prior exposure to basic machine learning concepts is recommended but not required.

Assessment

• Assignments: 50%

• Final Project: 50%

Course Content

• Introduction
  • Data Science in Economics
  • Technical Challenges
  • Data Analytics Methods
• Central Banks
  • Alternative Data Sources for Central Banks
• Textual Analysis of FOMC contents
  • Preparing Numerical Data
  • Preparing Textual Data
  • EDA on Numerical Data
  • EDA on Numerical Data
  • Create Training Datasets
  • Visualizing Features
  • Checking Baseline with AutoML
  • Predicting Sentiments of FOMC Corpus
  • EDA on Sentiments: Correlation
  • EDA on Sentiment Data
  • Visualize Features
  • Monetary Policy Shocks
  • Predicting the next decisions with tones
• ESG Ratings
  • Preparing training datasets
  • Improving classification datasets
  • Training Classifiers for ESG Ratings
  • Building econ_news_kr corpus
  • Predicting ESG Categories and Polarities
  • Cross validating datasets
  • Preparing active learning data
  • Putting them together in a pipeline