A data scientist and theoretical astrophysicist. I’m currently a Senior Data Scientist in Anti-Financial Crime at Trade Republic in Berlin. Previously I led BI, analytics and machine-learning initiatives as Senior Analytics Manager at Emmy / GoToGlobal, and before that I was a Research Scientist at the Max Planck Institute for Gravitational Physics (Albert Einstein Institute) and a member of the LIGO Scientific Collaboration, working on gravitational-wave physics and tests of general relativity.
Hi, I’m Abhirup 👋
Featured Work
Stille Ansprüche — German Social Benefits Discovery Assistant
RAG-based assistant that helps people discover German social benefits (Sozialleistungen) they may be entitled to but don't know exist — grounded in an official 500+ benefit inventory, with hybrid search and citations to the legal basis for every answer. Final project for the DataTalksClub LLM Zoomcamp.
Greenwash Radar — EU Taxonomy Sustainability-Disclosure Assessment
Assesses whether a corporate sustainability-disclosure excerpt aligns with the EU Taxonomy: a from-scratch PyTorch transformer and a fine-tuned ClimateBERT classifier as a fast pre-filter, backed by a citation-grounded RAG LLM agent that verifies every cited regulation Article against text it actually retrieved. Containerised with production-style monitoring (Prometheus/Grafana). Built for the DataTalksClub LLM Zoomcamp.
Fraud Detection with Graph Neural Networks
Graph-based fraud-detection system that models financial transactions as an entity-interaction network (users, accounts, devices, merchants) and applies GNNs to detect fraud rings, collusion and anomalous behaviour.
Sentiment-Enhanced Stock Predictor
Combines historical stock-market data with news-sentiment analysis to improve price forecasting, integrating financial time-series features with NLP-derived sentiment signals.