MSc in Survey Statistics and Data Analytics, ELTE

The last day of the final exam period—unprecedented outstanding results, with everyone earning top grades! The thesis topics were interesting and diverse, ranging from testing AI text detectors to soccer transfers, modeling Formula 1 overtaking maneuvers, customer segmentation, Monte Carlo simulations of healthcare delivery, and the macroeconomic application of Bayesian VAR models, all the way to survey representation of hard-to-reach income groups. In the photo, from left to right, are the committee and the recent graduates. It was a pleasure for us, the instructors, to conduct these three final exams with such enthusiastic and talented students; we wish you every success and happiness in the future!

We warmly congratulate today’s final exam takers, who set a new record: everyone received an A! The topics of the thesis research projects were once again diverse: ranging from evaluating the effectiveness of drones and anti-drone systems to analyzing fatigue in the Premier League and data visualization standards, all the way to machine learning applied to pancreatitis. (Pictured from left to right are the members of the committee and the recent graduates.)

We are delighted to congratulate the students who successfully passed their final exams in our MSc program in Survey Statistics and Data Analytics! The theses were of a high standard and covered a wide range of topics: ranging from polarization in Hungarian online media to drug trafficking on darknet markets, forecasting energy sector stock returns, machine learning applied to data on patients with aortic valve stenosis, and analyzing the co-starring networks of Hungarian film actors, all the way to an examination of the “15-minute city” concept. Pictured from left to right are the members of the final exam committee and the recent graduates.

Value Driven Data Science podcast, Episode 101: Why Traditional Statistics Still Matters in the Age of AI?
Why throwing data at an LLM is no substitute for building a model that understands the problem? What data scientists lose when they stop thinking probabilistically - and why it matters for decision making?
https://open.spotify.com/episode/2wdFEkN7dvnpvMzCdqAXhL?si=LJ1DOZxsT4umOEIvyBIPpw&fbclid=IwY2xjawSID-ZleHRuA2FlbQIxMABicmlkETFIQUdnYmduekduSlhDczU1c3J0YwZhcHBfaWQQMjIyMDM5MTc4ODIwMDg5MgABHh6LG7YQw_i2GC70VM6FzG0-HrhfqqOuXqu7BuLGl21qSWSROcXHgPJGOnsc_aem_hXQ6YmVnM_QFdf87FumSaQ&nd=1&dlsi=7dda93f6caca4752

Episode 101: Why Traditional Statistics Still Matters in the Age of AI Value Driven Data Science · Episode

A publication based on Alexandra Fodor's Survey statistics and data analytics MSc thesis.
The paper in Ampersand (Q1) examines whether LLMs are capable of annotating categories that are neither mutually exclusive nor trivial from a hermeneutic perspective.
The findings highlight both the potential and the interpretive limits of LLMs in social science applications, underscoring the importance of careful annotation design and the thoughtful integration of LLMs into human-centered workflows.
https://www.sciencedirect.com/science/article/pii/S2215039026000172

We warmly welcome Noa Delaporte, our Erasmus intern, to our department! You’ll likely see him around the department hallways from now on. Below is Noa’s introduction.
"I am currently a first-year Master’s student in Applied Mathematics and Statistics, specializing in Data Science and Artificial Intelligence at the University of Rennes 2 in France. As part of my studies, I have the opportunity to complete a research internship abroad at Eötvös Loránd University.
This internship allows me not only to apply my skills to meaningful research projects, but also to improve my knowledge and discover new fields that I might not have explored on my own.
Dávid Simon and Ágnes Hárs invited me to join their research project on return migration. My main task is to develop an AI-based tool using Large Language Models (LLMs) to automatically analyze textual data from migration-related interviews and documents.
A second part of my internship will focus on modeling migration duration using survival analysis methods in order to better understand the factors influencing return migration.
These projects are carried out under the supervision of Dávid Simon and contribute to ongoing interdisciplinary research combining data science, artificial intelligence, and migration studies."

Jakab is also an instructor for our MSc program.

Exciting experiments at our institute.

Ildikó Barna, Renáta Németh and Jakab Buda are instructors of our MSc program.