Research & Interests

My research focuses on the intersection ofSLMs, machine learning systems, and data-driven decision making, with particular emphasis on structured tasks such as classification and evaluation. I am interested in how compact models can achieve strong performance while remaining efficient, interpretable, and deployable in real-world settings.

I am especially interested in multi-class classification, benchmarking, and evaluation methodologies, and how model design choices such as distillation, quantization, and prompting strategies influence performance across domains. More broadly, my work engages with the growing role of SLMs as efficient alternatives to large-scale models, particularly for downstream and domain-specific applications.

I contribute to the research community through conference publications that explore the design, evaluation, and application of machine learning models. My work emphasizes practical and reproducible approaches to model evaluation, with a focus on real-world constraints such as efficiency, scalability, and interpretability.

Recent publications include:

Specialized text classification: an approach to classifying Open Banking transactions IEEE 18th International Conference on Computer Science and Information Technologies (CSIT), 2023

Keywords: Open Banking, specialized text classification, natural language processing, transaction descriptions

Income and salary detection from Open Banking transaction and payment data : a comparative methodological perspective The International Fintech Research Conference, University of Perugia, January 30-31, 2025

Keywords: Open Banking, specialized text classification, natural language processing, transaction descriptions

I regularly present my work at academic conferences and workshops, engaging with the research community on topics including SLMs, classification systems, and evaluation frameworks. These presentations allow me to discuss emerging challenges such as model reliability, benchmarking standards, and deployment trade-offs.

Recent presentations include:

Income and salary detection from Open Banking transaction and payment data: a comparative methodological perspective , International Fintech Research Conference, University of Perugia, January 30-31, 2025

Alongside my research, I teach data visualization with a focus on clarity, interpretability, and critical analysis. My teaching emphasizes not only how to create visualizations, but how to evaluate their effectiveness and avoid misleading representations.

I encourage students to approach visualization as a tool for reasoning and communication, considering how design choices shape interpretation and insight.

In parallel with my academic work, I develop software tools aimed at improving the quality and effectiveness of data visualizations. This work focuses on creating systems that guide users toward better design practices, reduce common visualization errors, and enhance the clarity of visual communication.

By combining research, teaching, and tool development, I aim to contribute to a more thoughtful, reliable, and impactful use of data across both academic and applied contexts.