Skip to content
View eorgantzoglou's full-sized avatar
  • Greece
  • 10:24 (UTC +03:00)

Highlights

  • Pro

Block or report eorgantzoglou

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
eorgantzoglou/README.md

Electrical & Computer Engineering graduate — AI / ML engineering, with a focus on LLM agent systems

I build applied machine learning and agent systems, and I keep the evaluation attached to them. That second half is the part I actually care about: a model reaching a number is easy, and knowing whether the number means anything is the work. Every repository here reports what failed next to what worked — my thesis opens with the finding that its own LLM contributed nothing, and it is a better piece of work for it.


Diploma thesis

Development of a Multi-Agent Portfolio Management System Using LLMs University of Thessaly, ECE · July 2026 · supervised by Georgios Thanos

A LangGraph orchestration layer sitting on top of deterministic quantitative tooling. Three specialised agents — data gathering, quantitative analysis, and risk & context — feed a Chief Investment Officer orchestrator that assembles the portfolio. Evaluated across 13 sequential backtest phases over 21 years of US market history, with survivorship bias removed through point-in-time index constituents.

The headline finding is a negative one, and the thesis leads with it: on an already-filtered, already-ranked candidate set, the LLM contributed no selection alpha. Removing it improved both strategies, and the damage scaled with call frequency — the opposite of what a component that adds value does. Establishing that across 13 phases, rather than asserting it, taught me more than a positive result would have.


Currently

AI Developer at Agrobox (part-time) — built a retrieval-augmented assistant that answers user questions over company data, and now building a custom AI agent on Google's Agent Development Kit over a FastAPI backend: tool integration, memory logic, file-upload handling, and structured multi-step interaction flows. Also ran the model-selection stage for a Greek voice-entry feature — see the speech-to-text benchmark below.


Selected projects

Smart support ticket triage — LLM-assisted labelling of a support-ticket corpus against a hand-built taxonomy, on the way to a small fine-tuned classifier behind a served endpoint. Still in development, so the repository is private for now.

Greek speech-to-text for voice entry — which model should ship, decided with data instead of a hunch. Three STT models on a Greek agricultural test set, scored on Word Error Rate and real-time factor after normalisation. Domain vocabulary turned out to be the whole ballgame: every model handles plain words, and the gap opens on product names and terms like «ουρία».

Technical-indicator evaluation — five feature-selection methods feeding a recurrent classifier across fourteen large-cap equities, with next-bar execution and realistic costs. Also where I caught an indicator that was leaking eleven days of future data and had topped every feature ranking in the first pass, then traced it with a lag test.

Deep learning for price forecasting — linear, tree and recurrent models (Random Forest, SVR, XGBoost, LSTM, GRU, RNN) across eight cryptocurrencies and three horizons, wrapped in a Streamlit interface, with the extrapolation failure of tree models on trending series documented rather than quietly dropped.

Clustering and classification at scale — K-Means, connectivity-constrained hierarchical clustering and DBSCAN against three classifiers on 100,000 airline passenger records. The interesting part is not the 94.8%; it is why no unsupervised method finds the boundary that supervised learning finds easily.

Recommender systems — item–item collaborative filtering against Neural Collaborative Filtering on a book-ratings corpus, including the unit artefact that made the neural model look 36× better than it was until the two scales were reconciled.


Tools I reach for

Languages

Python C C++ LaTeX

Machine learning & LLMs

TensorFlow Keras scikit-learn LangGraph Pandas NumPy

Applications & tooling

FastAPI Streamlit Jupyter Git


Direction

Agent systems that can be trusted about what they do. The discipline is the part worth keeping: chronological splits, held-out windows, a benchmark you are allowed to lose to, and a written record of what did not work. Plenty of people can get a model to a number — I would rather be the one who can tell you whether the number means anything.


Elsewhere

LinkedIn · Greece

Popular repositories Loading

  1. Development-of-a-Multi-Agent-Portfolio-Management-System-Using-LLMs Development-of-a-Multi-Agent-Portfolio-Management-System-Using-LLMs Public

    Multi-agent LLM portfolio management system with a 21-year walk-forward backtest (2005–2025). Diploma thesis, University of Thessaly.

    Jupyter Notebook 1

  2. Book-Recommender-System Book-Recommender-System Public

    Book recommender system comparing content-based, collaborative filtering and neural approaches (CNN embeddings, NCF) on public book-rating datasets. Semester project, University of Thessaly.

    Jupyter Notebook

  3. Agrobox-stt-project Agrobox-stt-project Public

    Speech to text project

    Python

  4. Scout-Equity-Research-VIBE-CODED- Scout-Equity-Research-VIBE-CODED- Public

    A global deep-research equity scout: harvests primary regulatory filings (SEC, ESEF, EDINET, OpenDART, Companies House), runs a cited LLM research pipeline over them, and scores the picks against d…

    Python

  5. Cryptocurrency-Price-Prediction Cryptocurrency-Price-Prediction Public

    Streamlit app forecasting eight cryptocurrencies over three horizons, backed by a comparison of seven model families. Data Mining semester project, University of Thessaly.

    Jupyter Notebook

  6. Stock-Prediction-Indicator-Evaluation Stock-Prediction-Indicator-Evaluation Public

    Do technical indicators predict next-day stock direction? ~80 indicators, five feature selection methods, a Bidirectional GRU and a vectorbt backtest say no — 50.75% accuracy, losing to buy-and-hol…

    Jupyter Notebook