Skip to content
View ntheofan's full-sized avatar

Block or report ntheofan

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ntheofan/README.md

Hi, I'm Theofanis Nikolaou 👋

Applied AI & Data Professional | Financial Analytics · RAG · Python · SQL


🧭 About Me

I bring 10 years of experience in financial operations, payroll analytics, and process automation at the Hellenic Army, combined with an MSc in Artificial Intelligence and Applications (University of Thessaly, grade 9.65/10). I'm currently building practical deployment skills — Docker, APIs, cloud — to complement that foundation.

  • 🎖️ Captain – Finance Corps, Hellenic Army — analyzing payroll & HR data for 55,000+ personnel
  • 🎓 MSc thesis on Retrieval-Augmented Generation for financial document analysis
  • 📊 Google Data Analytics–certified | SQL, Python, Power BI, Advanced Excel
  • 🧠 Mensa International member (IQ 133, 99th percentile)
  • 🌱 Currently learning: Docker, FastAPI, CI/CD, and cloud deployment (AWS)

🚀 Building: Financial RAG API

My MSc thesis, "Design and Empirical Evaluation of Retrieval-Augmented Generation Systems for Financial Document Analysis," evaluated dense, hybrid, and cross-encoder reranked retrieval pipelines over financial reports (BGE-M3 embeddings, FAISS, BM25, Reciprocal Rank Fusion, RAGAS/RAGChecker evaluation).

I'm now turning that academic pipeline into a deployed service:

  • Wrap the retrieval + generation pipeline in a FastAPI backend
  • Containerize with Docker
  • Deploy to a cloud host with a live, testable URL
  • Add basic monitoring/logging

Status: in progress. This section will be replaced with a live demo link and repo once deployed — no shortcuts, no placeholders pretending otherwise.


📚 Learning log

These are academic and self-study projects I've worked through — useful for understanding the underlying methods, not yet production systems. Repos will be linked here as they're cleaned up and published.

Topic What it covers
Mobile robot navigation A* path planning, Extended Kalman Filter localization, waypoint control (simulation)
ML fundamentals Decision trees, regression, Naive Bayes, Bayesian networks, Apriori, KNN, SVM, clustering, Q-learning
Computer vision / deep learning CIFAR-10/100 classification — KNN, MLP, and CNN comparison in TensorFlow/Keras
Generative models Vanilla GAN, DCGAN, cGAN, and WGAN-GP across CIFAR-10, CIFAR-100, and Fashion-MNIST, evaluated with FID and Precision/Recall

🎓 Certifications & Education

  • MSc, Artificial Intelligence and Applications — University of Thessaly (Grade: 9.65/10)
  • Diploma, Analysts–Programmers Program — Hellenic Army School of Computer Programmers (ΣΠΗΥ), 2024–2025 (Overall grade: 96.01/100)
  • Google Data Analytics Professional Certificate — Google, 2025
  • Microsoft Power BI Desktop for Business Intelligence — Udemy, 2025
  • Machine Learning A-Z: AI, Python & R — Udemy, 2025
  • Bachelor of Economics — Aristotle University of Thessaloniki, 2015 (Grade: 8.02/10)

📫 Let's connect

Athens, Greece 🇬🇷

Pinned Loading

  1. financial-rag-platform financial-rag-platform Public

    Evidence-grounded financial document intelligence with hybrid RAG, FastAPI, pgvector, Streamlit and reproducible retrieval evaluation.

    Python

  2. autonomous-robot-navigation-ekf autonomous-robot-navigation-ekf Public

    Python