Bachelor
2026/2027
Machine Learning in Finance
Type:
Elective course (HSE/NES Programme in Economics)
Delivered by:
Undergraduate Programmes Curriculum Support
Where:
Faculty of Economic Sciences
When:
4 year, 2 module
Open to:
students of one campus
Language:
English
ECTS credits:
3
Contact hours:
32
Course Syllabus
Abstract
The aim of this course is to introduce students to the fundamental concepts of supervised machine learning (ML) and its applications in finance. During the lectures, we will cover key ML methods—including classification and regression trees, ensemble techniques, and artificial neural networks—without delving deeply into technical details (though several proofs will be presented, and a solid mathematical background is required to follow the material). In homework assignments, students will learn how to apply these methods to financial problems such as index trading, derivative pricing, volatility forecasting, and portfolio selection. Students will also gain practical experience in working with financial data using ML techniques. In addition, participants will learn basic Python commands and complete practical exercises.
Learning Objectives
- To bridge finance and data science – equip students with a rigorous understanding of how machine learning techniques (from linear regression to deep learning) can be applied to financial data, while appreciating the unique constraints of the field: non‑stationarity, noise, and limited sample sizes. To develop hands‑on modeling competence – through practical assignments and case studies, enable students to independently build, tune, and validate predictive models for tasks such as credit risk assessment, algorithmic trading, fraud detection, and asset pricing, using real‑world financial datasets. To foster critical evaluation skills – train students to critically assess model performance, diagnose overfitting and look‑ahead bias, compare alternative approaches, and make informed trade‑offs between interpretability and accuracy, especially when models are used for high‑stakes decisions. To embed ethical and regulatory awareness – cultivate an understanding of the legal, ethical, and societal implications of ML in finance, including fairness, explainability (e.g., GDPR right to explanation), model governance, and the responsible use of alternative data, so that students can design systems that are not only profitable but also trustworthy and compliant.
Expected Learning Outcomes
- Apply core machine learning algorithms (e.g., regression, classification, tree‑based models, and neural networks) to solve real‑world financial problems such as asset price prediction, credit scoring, and algorithmic trading, while critically evaluating model performance using appropriate metrics. Handle and preprocess financial data – including time series, panel data, and alternative data sources.
Course Contents
- Recurrent ANN for predicting financial time series, e.g., volatility forecasting
- ML in portfolio choice problems
- Introduction to Artificial Neural Networks (ANN)
- Random forest, bagging and boosting with application to default predictions to shadow CDS pricing and default predictions
- Classification and regression trees with application to Fama-French five-factor model
- Regularization in liner models with application to index tracking
- Basic concepts of ML
Assessment Elements
- Домашние заданияStudents are assumed to have sufficient background in econometrics and finance theory (e.g., they are expected to be familiar with the meaning of volatility). Each week a problem set dedicated to practical application of concepts covered in lectures will be distributed. Completing this homework will be counted for 66% of the final grade.
- Финальная контрольнаяThe 2-hour-long final written format A4 exam will give 34% of the final grade.
Bibliography
Recommended Core Bibliography
- An Introduction to Statistical Learning, with Applications in R, Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Science+Business Media, LLC, part of Springer Nature 2021, 978-1-0716-1418-1, published: 29 July 2021
Recommended Additional Bibliography
- Hastie, T., Tibshirani, R., & Friedman, J. H. (2009). The Elements of Statistical Learning : Data Mining, Inference, and Prediction (Vol. Second edition, corrected 7th printing). New York: Springer. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=277008