Research Seminar "Data Analysis in Applied Research"

2026/2027

Academic Year

ENG

Instruction in English

4

ECTS credits

Delivered at:

School of Data Analysis and Artificial Intelligence

Course type:

Compulsory course

When:

3 year, 1-4 module

Instructor

Gromov, Vasilii

Course Syllabus

Abstract

The specialization seminar offers the opportunity to study subjects and sections of mathematical statistics related to the application of differential equations, machine learning, probability theory and mathematical for modeling various solutions of a wide range of theoretical and applied problems. These tasks include modelling of real-world systems using catastrophe theory and self-organization theory. The computational methods used are standard for machine learning: clustering, pattern recognition, dimension reduction. The purpose of the research seminar is to expand the research horizons of students. It is assumed that at the end of the course, the student will be able to prepare a research paper or grant application. To do this, the student will be involved in the following activities: attending classes (it is obligatory), analyzing a large number of sources in a foreign area for the student in order to learn how to highlight mathematical problems in non-mathematical articles, completing part of a group project, preparing presentations and discussion (peer review) of other people's projects and presentations. Prerequisites Knowledge of basic mathematics: analysis, linear algebra, probability theory, - algorithms, programming fundamentals, the ability to understand computational packages

Learning Objectives

• Be able to prepare and conduct a presentation with a report on a scientific topic, as well as conduct an academic discussion on the materials of the report.
• To be able to independently choose and study modern scientific articles, find relevant literature.
• Be able to write scientific texts.

Expected Learning Outcomes

• Be able to prepare and conduct a presentation with a report on a scientific topic, as well as conduct an academic discussion on the materials of the report.
• Methods for verifying empirical results: hypothesis testing, bootstrap, randomization, etc.
• Methods of mathematical modeling based on (stochastic) differential equations, probability theory.
• Modern computational methods used in related fields, in particular, when forecasting time series and solving inverse problems (Fourier analysis, wavelets, regression, SSA, dimension reduction, moving averages, neural networks, filters, etc. - understanding the advantages and disadvantages each of the methods.
• To be able to independently choose and study modern scientific articles, find relevant literature. Be able to write scientific texts.

Course Contents

• Invited talks.

Assessment Elements

• Course paper presentation
• Colloquium
• Report
• Review

Interim Assessment

• 2026/2027 4th module
  Final grade = Module 1 * 0.3 + Module 2 * 0.3 + Module 3 * 0.3 + Module 4 * 0.1; where Module 1 = (report 16 points + review 4 points + colloquium 10 points) / 100; Module 2 = (report 16 points + review 4 points + colloquium 10 points) / 100; Module 3 = (report 16 points + review 4 points + colloquium 10 points) / 100; Module 4 = (thesis presentation 10 points) / 100.

Bibliography

Recommended Core Bibliography

• Algorithmic trading : winning strategies and their rationale, Chan, E. P., 2013
• Empirical market microstructure : the institutions, economics, and econometrics of securities trading, Hasbrouck, J., 2007

Recommended Additional Bibliography

• Pattern recognition and machine learning, Bishop, C. M., 2006

Authors

• Gromov Vasilii Aleksandrovich