Master
2021/2022
Big Data and Machine Learning With Applications to Economics and Finance
Type:
Elective course (Financial Economics)
Area of studies:
Economics
Delivered by:
International College of Economics and Finance
When:
2 year, 1, 2 module
Mode of studies:
distance learning
Online hours:
10
Open to:
students of one campus
Master’s programme:
Financial Economics
Language:
English
ECTS credits:
4
Contact hours:
70
Course Syllabus
Abstract
Big Data and Machine Learning (M.Sc. level) is an advanced elective course designed for masters students at ICEF. The course is open to all second year M.Sc. students. Knowledge of the Python programming language is strongly advised but not required. Students without Python knowledge will be expected to exert additional effort during the first few weeks of the course to catch up. The course is taught in English. The course has three broad sections: I. Building skills using Python libraries to solve common problems in the analysis of financial data. II. Designing and implementing interpretable machine learning models. III. Getting acquainted with deep learning principles and applications, including large language models.
Learning Objectives
- The main objective of the course is to endow students with fundamental skills related to data mining and analytics, as well as with designing and implementing machine learning predictive models.
Expected Learning Outcomes
- - Analyze multiple data sources
- - Apply clustering and anomaly detection methods
- - Be able to code simple algorithms using Python
- - Be able to setup a neural network
- - Convert text into input for machine learning algorithms
- - Find solutions to optimization problems using Python
- - Present data graphically
- - Train a ML regression. Make predictions
- - Train an ML classifier. Make predictions
- - Use data structures to store and transform data
- - Use Python to solve simple analytical tasks
- - Use web applications API to obtain data
Course Contents
- Introduction to Python
- Python’s Scientific Stack: NumPy, Pandas, and SciPy
- Data Visualization
- Financial and Other Applications
- Mathematical tools and numerical calculus
- Big Data
- Introduction to Data Mining
- Mining the Social Web
- Textual Analysis
- Machine Learning Classification Methods
- Machine Learning Regression Methods
- Neural Networks. Forecasting Stock and Commodity Prices
Assessment Elements
- project proposal
- intermediate report
- a final report and presentation
- attendance and participation
- home assignments
- examIn order to get a passing grade, students must obtain an exam grade of 25/100 or higher. Online format.
Interim Assessment
- 2021/2022 2nd module0.3 * exam + 0.05 * project proposal + 0.05 * attendance and participation + 0.1 * intermediate report + 0.2 * home assignments + 0.3 * a final report and presentation
