Spark Sessions 004
The Spark Sessions are a recurring event of the Data Science Initiative at the Faculty of Computer and Information Science. They are designed to facilitate the exchange of ideas and inspiration. The event consists of several snappy (5-7 min) presentations, followed by a casual gathering with refreshments:
1. On the Surprising Benefits of Vibe-Coding for Interdisciplinary Collaboration by Boshko Koloski (Young Researcher, Jozef Stefan Institute)
Stepping midstream, inter-disciplinary project—where documentation is sparse and data are disorganized—poses a significant challenge. Thanks to recent advances in LLMs, live “vibe-coding” workshops now offer a practical way to bridge those gaps. In this talk, I will present case studies from interdisciplinary collabs which real-time LLM-driven coding enabled teams to explore, prototype, and co-construct understanding on the fly, even under tight deadlines and uncertain conditions..
2. Automated Assignment Grading with Large Language Models: Insights From a Bioinformatics Course by Pavlin Poličar (assistant, UL FRI)
Are LLMs ready to replace TAs and grade student assignments? In a blind study conducted at UL-FRI, we tested whether LLMs are able to grade student submissions and generate written feedback with the same accuracy and quality as human TAs. We compared six LLMs—both commercial and open-source—and found that, with the right prompts, LLMs can achieve human-level performance both in terms of grading and feedback.
3. A General Approach to Visualizing Uncertainty in Statistical Graphics by Bernarda Petek (PhD student and researcher, UL FRI)
Quantifying and communicating uncertainty is integral to scientific communication. Despite this, it's often neglected. Without general methods or guidelines, practitioners must rely on niche, domain-specific techniques or create ad hoc solutions that are time-consuming, complex, and error-prone. All this narrows how uncertainty is taught and understood. In this talk, I will present our new general approach to visualizing uncertainty and bootplot, our open-source Python implementation.
4. Automating Value Investing: A Data Scientist's Journey into Finance by Lidija Jovanovska (Senior Data Scientist, Sportradar)
Explore the intersection of data analysis and personal finance. This talk illustrates the use of Python for analyzing financial data, enabling programmatic stock screening and informed personal finance decisions.
5. Trials & tribulations of pre-flight scoring in online advertising by Vid Stropnik (Data Scientist, Celtra)
Discover how Celtra built its first pre-flight ad scoring model—turning ad design into a data-powered prediction game! From wrangling Meta’s graph API chaos to debating regressors vs. classifiers, we’ll explore the messiness of creative performance, why “good” is all relative, and what it takes to forecast ad success before it ever goes live.
6. Snacks and drinks and discussions
