(in Polish) Sztuczna inteligencja w finansach 2600-IADz1SIF
Students will become familiar with AI technologies, in particular machine learning (ML), and their practical applications in the analysis of large datasets and human–computer interaction. The aim of the course is to develop skills in the use of ML tools to support decision-making. Participants will learn to identify both the opportunities and the limitations of implementing ML-based solutions in the context of data analysis.
The topics covered will include the following areas:
1. Data sources and data analysis environments.
2. Characteristics of data processed using machine learning algorithms.
3. Data evaluation and visualization.
4. Data preparation, standardization, and dataset splitting.
5. Selected machine learning algorithms and examples of their applications:
- Support Vector Machines (SVM)
- Classification Trees
- Random Forests (RF)
- K-means clustering
- Neural Networks
6. The prediction process.
7. Advantages and limitations of the discussed algorithms.
8. Examples of applications of the discussed algorithms in classification and regression tasks.
The discussion-based classes will be conducted using basic programming skills in the R environment and external packages appropriate for the machine learning algorithms covered in the course.
Course coordinators
Type of course
Learning outcomes
K_W01 The student can design and critically evaluate the process of implementing artificial intelligence algorithms in financial institutions, integrating advanced quantitative methodology (economics and finance) with corporate governance requirements (management) and restrictive regulatory frameworks regarding model explainability and data protection (legal sciences).
K_W05 The student can perform a multi-faceted analysis of the impact of megatrends (technological, ecological, and socio-political) on the architecture of AI information systems, assessing their significance for the financial stability of organizations and identifying fundamental ethical and legal dilemmas of digital civilization in automated decision-making processes.
K_W07 The student possesses in-depth knowledge of advanced information technology techniques and numerical methods (including optimization and stochastic algorithms) necessary for solving complex financial problems and is familiar with specialized software and programming environments used in the financial sector for modeling, data analysis, and automation of decision-making processes.
K_W06 The student identifies and applies the principles of industrial property protection and copyright law in the process of creating and operating AI systems, resolving dilemmas regarding the legal status of training data, the patentability of algorithmic solutions, and the rights to works generated by artificial intelligence in the financial sector.
K_U03 The student is able to independently and collaboratively prepare analyses, diagnoses, and reports concerning complex and atypical problems related to digital finance in organizations, present them communicatively to diverse audiences, and lead debates—also in English—using advanced information and communication tools.
K_U06 The student can independently and in a team develop advanced analyses and reports on atypical digital finance problems, and subsequently present them communicatively (also in English) to various audiences and conduct debates, utilizing modern ICT tools while considering the legal, ethical, and civilizational context.
K_U08 The student demonstrates a readiness for the critical assessment of their own knowledge and skills and possesses the capacity for self-directed learning and continuous professional development in the dynamically changing field of financial technology, while also actively supporting others in their professional growth by promoting a culture of learning and sharing specialized knowledge within the organization.
K_K05 The student can independently and collaboratively develop advanced reports on complex digital finance problems and communicatively present them (also in English) using ICT tools, demonstrating full responsibility for observing and developing professional ethical standards and fostering the heritage of the financial profession in the era of algorithmization.
Assessment criteria
Midterm exam (e.g., an online test on the e-learning platform) and participation.
Practical placement
Professional internships are not required for completing the course.
Bibliography
1. Przewodnik po pakiecie R, Przemysław Biecek, OFICYNA WYDAWNICZA GiS, 2017
2. Sztuczna inteligencja w finansach. Yves Hilpisch, Helion, 2022
3. Praktyczne uczenie maszynowe, Marcin Szeliga, PWN, 2019
4. Uczenie maszynowe w języku R, Brett Lantz, Helion, 2024
5. Język R w data science, Hadley Wickham, Mine Çetinkaya-Rundel, Garrett Grolemund, Helion, 2024.