Skip to content
View Mstfakts's full-sized avatar
47 followers · 71 following

Achievements

Achievement: Pull SharkAchievement: Starstruckx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull SharkAchievement: Starstruckx2Achievement: Arctic Code Vault Contributor

Block or report Mstfakts

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
Mstfakts/README.md

Hi, I'm Mustafa Aktaş 👋

Big Data Engineer · Data Scientist · ML Engineer
I build scalable ML systems on Apache Spark and production-grade data/AI pipelines with Docker/Kubernetes.

  • 🧠 Focus: Big Data ML (SparkML/PySpark), MLOps, ML Engineering, Anomaly Detection
  • 🏢 Current: TÜBİTAK BİLGEM — Cloud Computing and Big Data Research Laboratory (B3LAB)
  • 🎓 MSc CS @ Istanbul Technical University

Selected Projects

Machine Learning

Project ⚙️ Description 📝 Stars ⭐
Building-Detection-MaskRCNN Building detection with Mask R-CNN Stars
Federated-Learning-Comparative-Study Federated learning experiments + comparative evaluation (Flower, fairness) Stars
Knowledge-and-Dataset-Distillation Knowledge and Dataset Distillation on the MNIST Dataset Stars

Vector Search / RAG

Project ⚙️ Description 📝 Stars ⭐
Text-Similarity-Towhee-MilvusDB Similarity search using embeddings and Milvus Stars

Reinforcement Learning

Project ⚙️ Description 📝 Stars ⭐
Dinosaur-Game-with-Deep-Q-Learning DQN agent for the Chrome Dino game Stars
DRL-Competition 2024 Deep Reinforcement Learning (DRL) agents to learn resource collection and combat Stars

Tech Stack (the stuff I actually use)

Big Data / Lakehouse: PySpark · SparkML · Iceberg · S3 · SQL · MongoDB
Messaging: Kafka · MQTT
Monitoring: Airflow · Grafana
Analytics: Apache Druid · Superset
ML/LLM: PyTorch · (TensorFlow) · Ollama · LangChain
DevOps: Docker · Kubernetes · CI/CD · Git · Linux
Backend: Python · Go · REST · GraphQL

Publications

  • Enhancing Credit Risk Assessment with Federated Learning (EAI ROSENET 2024) Access
  • Small Object Detection and Tracking from Aerial Imagery (UBMK 2021) Access

Contact

Pinned Loading

  1. Building-Detection-MaskRCNN Building-Detection-MaskRCNN Public

    Building detection from the SpaceNet dataset by using Mask RCNN.

    Jupyter Notebook 267 22

  2. Text-Similarity-Towhee-MilvusDB Text-Similarity-Towhee-MilvusDB Public

    A Milvus Database and NLP project where you can perform text-based similar searches on the dataset you will upload. Milvus Database is a vector Database and Towhee provides several advantages such …

    Jupyter Notebook 1

  3. Dinosaur-Game-with-Deep-Q-Learning Dinosaur-Game-with-Deep-Q-Learning Public

    Play "Google Chrome Dinosaur" game via Deep Q Learning

    Python 1

  4. College-Management-System College-Management-System Public

    College management system for universities. Log in as a student or a lecturer. PHP, MySQL, HTML, Bootstrap, Xampp, PhpMyAdmin were used.

    PHP 76 28

  5. BackendVideoShare BackendVideoShare Public

    This project was done for the C++ (Programming for Engineers) course in 2019-2020 Fall.

    C++ 3

  6. ClassReservationSystem/ClassReservationSystem ClassReservationSystem/ClassReservationSystem Public

    CSS