Skip to content
View Eyna-A's full-sized avatar
13 followers · 13 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Organizations

@AI-Builders-Iran

Block or report Eyna-A

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
Eyna-A/README.md

Header Banner

Typing SVG

Building production-ready ML architectures, autonomous agentic workflows, and quantitative engines.

Gmail Badge LinkedIn Badge GitHub Badge

⚡ About Me

  • 🔬 Focus Areas: Deep learning architectures, autonomous AI agents (LangChain/LangGraph), and quantitative research pipelines.
  • 🛠️ Diagnostics-First Philosophy: I build machine learning systems with strict validation gates—every signal and model behavior is challenged before deployment.
  • 🚀 SaaS & Entrepreneurship: Passionate about taking AI innovations from 0 to 1, creating scalable, real-world software products.
  • 🎵 Interdisciplinary Interests: Exploring non-obvious intersections of AI with domains like quantitative finance and music.

🛠️ Tech Stack Grid

Category Badges
Languages Python SQL
AI / ML Frameworks PyTorch TensorFlow HuggingFace LightGBM XGBoost Scikit-Learn
Agents & Vision LangChain LangGraph OpenCV
Data & Databases PostgreSQL SQLite Pandas NumPy
Tools & Infrastructure Docker Git FFmpeg Jupyter

🌟 Featured Engineering Projects

Project Description Tech Stack Highlights
TSE Robo-Advisor End-to-end ML pipeline for signal research, statistically-validated backtesting, and portfolio optimization on the Tehran Stock Exchange with a diagnostics-first gate. Python LightGBM SciPy SQLite React Purged K-Fold CV, SLSQP optimization, atomic JSON exports, and stale-ticker guard.
Brain Tumor Classification Custom CNN architecture for classifying brain tumor types from MRI scans. Trained with strict validation techniques. PyTorch Keras OpenCV Google Colab ~88% test accuracy on Kaggle MRI dataset. Colab-ready pipeline.
Designed & Developed by Eyna Shabani • Driven by curiosity & statistical rigour.

Pinned Loading

  1. AI-Risk-Management-System AI-Risk-Management-System Public

    A comprehensive AI-driven system for predicting financial risk and market volatility using deep learning models (LSTM, Attention) and quantitative finance techniques.

    HTML

  2. AI-Video-Understanding-Pipeline AI-Video-Understanding-Pipeline Public

    AI-powered pipeline that transforms videos into structured knowledge. It downloads a video, extracts audio, transcribes speech, translates content into Persian, organizes it into academic-style not…

    Python

  3. Brain-Tumor-Classifier Brain-Tumor-Classifier Public

    A Convolutional Neural Network (CNN) model for brain tumor detection using MRI images.

    Jupyter Notebook