About

Teacher, historian, technician, developer — analyst by obsession. I built GEOPOL Analytics because I needed a tool that didn’t exist — one that could ingest thousands of sources, detect patterns across domains, and present a coherent picture of what’s happening in the world.

My path has been deliberately cross-disciplinary: a degree in History (palaeography & archival science), a Master’s in Educational Sciences (scientific & technical specialisation), and a certification in industrial maintenance. I spent years in energy systems inspection — domestic gas compliance, industrial electrical controls — before returning to what I love most: teaching and learning. Above all, I am driven by curiosity and the desire to transmit knowledge.

History and archival science gave me the analytical frameworks: how power structures evolve, how narratives shape perception, how primary sources must be read with method and suspicion. Education taught me to structure complexity and make it accessible. Industrial experience gave me systems thinking, operational rigour, and a healthy respect for what happens when theory meets reality. What was missing was a way to apply all of this at scale, in real time, across languages and platforms. So I started building.

This project is a one-person operation — from the NLP pipelines to the game-theoretic models, from the server administration to the frontend design. Every line of code, every analytical choice, every design decision reflects a single perspective trying to make sense of complexity.

Traditional intelligence analysis requires teams of specialists, expensive data subscriptions, and institutional backing. GEOPOL Analytics is an experiment: can a single developer, using open-source tools and free-tier APIs, build something that approaches the depth of institutional analysis?

The answer, after months of development, is nuanced. The system can ingest and correlate data at a scale no human could match manually. But it is also limited by one person’s time, one server’s resources, and the inherent biases of the sources it consumes. Transparency about these limitations is not a weakness — it’s the methodology itself.

Every analytical choice is documented in the Methodology section. Every data source is identified. Every algorithm is explained. If you disagree with a conclusion, you can trace it back to the evidence and the reasoning that produced it. That is the standard this project holds itself to.

Built with open-source technologies and a commitment to sovereignty over data and infrastructure. No cloud lock-in. No third-party analytics. No tracking.