Бакалавриат 2026/2027

Методы работы с данными для экономистов

Статус: Курс по выбору (Международная программа по экономике и финансам)

Кто читает: Международный институт экономики и финансов

Где читается: Международный институт экономики и финансов

Когда читается: 3-й курс, 2 семестр

Охват аудитории: для своего кампуса

Язык: английский

Кредиты: 4

Контактные часы: 64

Course Syllabus

Abstract

This course introduces students to data science for economics and finance. It combines core machine learning methods, text analysis, and practical applications using Python. The lectures cover the main concepts and tools of machine learning, including regression, classification, resampling, model selection, non-linear models, tree-based methods, and unsupervised learning. The course also introduces text analysis, including how to represent text as data, preprocess textual information, and apply methods such as dictionary-based analysis and topic modeling. The final part connects machine learning with econometrics and discusses how these tools can be used in empirical economic research. The seminars provide hands-on training in Python and give students the opportunity to apply the methods covered in the lectures to structured and unstructured datasets. They begin with a review of the foundations of Python, including objects, data types, data structures, indexing, control structures, and functions. Students will then use standard data science workflows to prepare, explore, visualize, analyze, and model data with tools such as NumPy, Pandas, Matplotlib, and relevant machine learning libraries. By the end of the course, students will be able to use Python to implement common machine learning and text analysis methods, evaluate model performance, and apply data science tools to economic and finance questions.

Learning Objectives

• The course aims to introduce students to the main concepts, tools, and applications of data science in economics and finance. It develops both conceptual understanding and practical skills, with an emphasis on applying machine learning and text analysis methods to real-world data.
• More specifically, the course aims to help students: • understand the logic of statistical learning and machine learning; • connect data science methods to economic and finance questions; • develop practical skills in Python for data analysis; • evaluate the strengths and limitations of different machine learning methods; • understand how text can be transformed into data and used for empirical analysis; • appreciate how machine learning can complement econometric approaches in applied research.

Expected Learning Outcomes

• write simple programs in Python using basic data structures, control structures, and functions
• use Python libraries such as NumPy, Pandas, Matplotlib, and machine learning packages to manipulate, analyze, and visualize data
• apply core ideas from statistical learning, including prediction, model evaluation, overfitting, training and test error, and resampling methods
• implement and interpret supervised learning methods, including OLS, classification methods, model selection techniques, non-linear models, and tree-based methods
• understand selected statistical properties of estimators, including unbiasedness, consistency, and asymptotic distributions
• implement and compare algorithms such as regression trees, classification trees, bagging, random forests, and boosting
• apply unsupervised learning methods such as principal component analysis, k-means clustering, and hierarchical clustering
• analyze text data by preprocessing documents, writing basic regular expressions, representing text as data, and applying dictionary-based methods, text-classification, and topic models
• use simulations and real-world datasets to study the performance of estimators and algorithms
• formulate research questions for which machine learning methods and/or text data can provide useful evidence
• understand how machine learning methods can complement econometric analysis in applied research

Course Contents

• Course Introduction
• Basic Machine Learning Concepts
• Linear Regression
• Classification
• Resampling Methods
• Linear Model Selection and Regularization
• Non-linear Models
• Tree Based Methods
• Unsupervised Learning
• Text Analysis I: Representing Text as Data
• Text Analysis II: Methods and Applications
• Econometrics Meets Machine Learning

Assessment Elements

• assignment 1
• assignment 2
• Final Exam
  In order to get a passing grade for the course, the student must sit (all parts) of the examination.
• Attendance

Interim Assessment

• 2026/2027 2nd semester
  0.1 * Attendance + 0.1 * assignment 1 + 0.1 * assignment 2 + 0.7 * Final Exam

Bibliography

Recommended Core Bibliography

• Learning Python : [covers Python 2.5], Lutz, M., 2008
• The elements of statistical learning : data mining, inference, and prediction, Hastie, T., 2017

Recommended Additional Bibliography

• Data mining : practical machine learning tools and techniques, Witten, I. H., 2011

Authors

• Lagios Nikolas