Data Science (Márton Rakovics)

The aim of the course is to review the fundamentals and most important methods of data science (machine/statistical learning, data mining). The course approaches the discussed methods from the point of view of the general problem of function approximation, and then presents the main solutions and their relationship. During the practical sessions, the students can deepen their knowledge acquired in the lecture with the help of data analysis examples and their own method implementations – carried out in R.

Programming I–II. (Jakab Buda, Eszter Katona, Júlia Koltai, Zsófia Rakovics)

In the second course, students learn the basics of the Python programming language (types of variables, basic commands, functions, loops, databases and the types of data stored in them). After the basics, we pay special attention to the webscraping and the use of APIs among the possibilities inherent in the program. During the course, we also deal with the SQL language in a smaller number of hours. We also present the embedding of SQL in Python.

Data Analysis I. (Renáta Németh, Blanka Szeitl)

In the course, we learn about basic data analysis methods and their practical applications. We work on generalized regression models and basic methods also used in data mining. During the processing, the computational implementation of the methods is also described, using databases available online. The class will also function as a reading seminar in order to make it easier for the students to independently learn new methods in the future.

METHODS

• linear regression – categorical predictors, interactions
• ANOVA and linear regression. Multiway ANOVA, unbalanced design, sequential sum of squares
• logistic regression
• the former in a single framework: Generalized Linear Models
• decision trees (Classification And Regression Tree, CART) as an alternative to logistic regression
• text mining, some simple models and R-packages
• loglinear models in SPSS, relationship with logistic regression 

GENERAL CONCEPTS

• confounding, controlling
• interactions
• model fitting, fit measures
• model building (stepwise methods)
• testing nested models
• overfitting, validation, k-fold crossvalidation, bootstrap e.g. for variable selection

Qualitative Methods (Anikó Gregor)

The aim of the course is to give an introduction to the qualitative methodology used in market research, together with the related practical, sampling and ethical problems. During the semester, three qualitative methods will be learned in detail: observation, interview and focus group. We also cover the use of digital technologies, such as camera surveillance and online interviews. Through practical examples and case studies, we get to know how the methods work, and the students complete tasks related to all three methodologies in order to gain insight into their application. In the second half of the semester, important aspects of the analysis of the collected data will be discussed, and finally, we will review some aspects of the report and presentation concluding the qualitative research.

Network Analysis (Dávid Simon)

The course is an introduction to the basics of network analysis, relying on the mathematics of graph theory and the analysis packages of R and Python in terms of practical implementation. Students will be able to critically evaluate researches using network methodology both in the case of small-scale networks (where the focus is on individual nodes) and in the case of large-scale networks (where graph structure and constraint properties are more important). They will also be able to conduct a network analysis.

Data Analysis Infrastructure (Git, SQL and other tools)

This course is designed to provide a foundation for the most important elements of the data analysis infrastructure, which includes tools such as SQL, Git, and other essential resources. Participants will gain proficiency in SQL to extract and manipulate data and learn how to use Git, which is a powerful version control system for collaborative data analysis project management. During the course, students will be introduced to a number of additional tools and resources that are essential for data analysis workflows. The goal is for students to confidently navigate data analysis tasks in both professional and research environments. The practice-oriented course combines theoretical knowledge with practical application. Participants will gain proficiency in leveraging this infrastructure for fluid collaborative data analysis, preparing for the demands of data-driven industries.

Market Research I. (Tamás Géczi, András Máth, Katalin Melles)

It is possible to carry out market research with a wide variety of pre-qualifications. In this competition, however, the survey-statistical and data analytical background is an advantage – if students also get to know the methodological and theoretical background of market research. The course aims to acquire this set of knowledge in two semesters. The purpose of the first semester is to present and supplement the necessary background knowledge so that the students will be better able to adapt to the real market expectations after graduating.

Topics:

• Participants of the market research profession
• Basics of business economics
• Introductory marketing
• Practical marketing
• Basic techniques (U&A, brand research, advertising research, media research, panel research, service research)