Tomaz Bratanic is a network scientist at heart, working at the intersection of graphs and machine learning. Where most practitioners see tables, Tomaz sees relationships, and he has spent his career showing how modeling those relationships directly, with graph algorithms and graph neural networks, can answer questions that conventional machine learning struggles with.

He is the author of Graph Algorithms for Data Science, published by Manning. The book walks readers from core graph algorithms through machine learning on graphs to graph neural networks, with nearly every chapter built around a hands-on tutorial project, and it has become a practical entry point for data scientists who want to add network analysis to their toolkit.

Tomaz has applied these techniques across a wide range of domains: detecting fraud in financial transactions, exploring biomedicine, supporting business-oriented analytics, and building recommendation systems. He shares his work openly with the community through writing, code, and talks, including deep dives into how GNNs relate to other deep learning architectures and when graphs are, and are not, the right tool for the job. His combination of theoretical grounding and applied project experience makes him one of the clearest voices working on graph data science today.