Machine Learning in Finance 2600-DIdzMLFkf

Upon completion of the course, the student:

Knowledge
S_W01 – knows and deeply understands the research methodology and terminology related to machine learning, including fundamental concepts of regression, classification, model selection, and algorithm operation (SVM, k-NN, decision trees, neural networks).

S_W05 – knows and understands complex technological processes and phenomena and their impact on the development and application of machine learning methods in economic and financial data analysis, including model limitations and fundamental dilemmas related to the automation of decision-making processes.

S_W07 – knows the principles of creating and developing innovative machine learning-based solutions, including applications in entrepreneurship at national and global levels.

Skills
S_U01 – is able to use machine learning knowledge to recognize, diagnose, and solve prediction and classification problems in economics and finance.

S_U02 – is able to correctly interpret the results of complex machine learning processes (e.g., estimation errors, model fit measures) and assess their impact on financial and economic decisions.

S_U03 – is able to select appropriate data sources and apply relevant machine learning methods and tools (linear models, LASSO, Ridge, decision trees, ANN), as well as develop new analytical solutions tailored to the specifics of the problem being studied.

S_U04 – is able to formulate and test research hypotheses using machine learning methods and critically analyze the results obtained.

S_U05 – is able to propose solutions to prediction and classification problems under conditions of uncertainty and unpredictability, using appropriate machine learning algorithms.

S_U06 – is able to independently and collaboratively prepare analyses and reports utilizing machine learning methods, present them to diverse audiences (including in English), and lead a debate using advanced IT and communication tools.

Social Competencies
S_K01 – is able to evaluate and critically assess the application of machine learning methods in financial and economic data analysis, taking into account their limitations and decision-making consequences.

S_K02 – recognizes the importance and value of scientific knowledge in the context of applying machine learning to solve complex economic and financial problems, and is able to utilize the opinions of experts and specialists.

S_K03 – is able to initiate activities based on machine learning solutions that benefit the community, organizations, and the environment, including taking actions for the common good.

Project
Preparation of a project according to the instructor's guidelines based on market data. The project should consist of:
• theoretical description of the phenomenon
• data description
• model description
• results
• conclusions
summary and limitations

Internship are not required for this course

Cerulli, G. 2023. Fundamentals of Supervised Machine Learning with Application in Python, R and Stata. Springer, Cham, Switzerland.
Chollet, F. 2020. Deep Learning with Python. Apogeo.
Lakshmanan, V., Robinson, S., Munn, M. 2020. Machine Learning Design Patterns. O'Reilly Media.

Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system:

• Description of 2600-DIdzMLFkf in USOSweb