Financial Databases and Data Processing

2025/2026

Academic Year

ENG

Instruction in English

3

ECTS credits

Delivered at:

School of Finance

Course type:

Elective course

When:

1 year, 3 module

Instructors

Babynin, Andrey

Ryabikov, Ilya

Tomtosov, Aleksandr

Course Syllabus

Abstract

The course is devoted to building queries to unload financial data and writing Python programs for further processing and hypothesis testing. The course consists of three parts: 1) The unit on databases includes working with the Wind terminal through the MS Excel add-in and offloading financial data from Yahoo Finance, Fred, and the Kenneth French database. Data processing includes cleaning outliers, bringing tables with different financials to a standard format, and constructing benchmarks. Hypothesis testing uses standard econometric methods for large datasets and practice-oriented methods, including fundamental indexing and portfolio construction techniques. 2) An overview of graph methods in business. Modern ML and practical applications. Anti-fraud, customer segmentation, and risk identification. 3) AI and ML techniques in banking analytics.

Learning Objectives

• - Understanding how to use Python for getting financial data, including stock market data, financial report data, and alternative data.
• - Understanding how to use ML techniques for business analytics
• - Be able to apply AI and ML tools for analysing banking performance.

Expected Learning Outcomes

• Be able to collect financial data from Windows, Yahoo Finance, and FRED databases using Excel and Python add-ins.

Course Contents

• Financial databases and data processing
• Modern ML and practical applications in business
• AI and ML techniques in banking analytics.

Assessment Elements

• Test
  Test is based on ML in business analytics topics
• Project in AI and ML in banking
  Project is based on a AI and ML methods in banking topics
• Project with financial databases

Interim Assessment

• 2025/2026 3rd module
  0.4 * Project in AI and ML in banking + 0.3 * Project with financial databases + 0.3 * Test

Bibliography

Recommended Core Bibliography

• Nelli, F. (2018). Python Data Analytics : With Pandas, NumPy, and Matplotlib (Vol. Second edition). New York, NY: Apress. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1905344
• Python for data analysis : data wrangling with pandas, numPy, and IPhython, Mckinney, W., 2017

Recommended Additional Bibliography

• Pandas for everyone : Python data analysis, Chen, D. Y., 2023

Authors

• TOMTOSOV ALEKSANDR FEDOROVICH