Skip to content
View mahdikheirkhah's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report mahdikheirkhah

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
mahdikheirkhah/README.md

Hi there, I'm Mohammad Mahdi Kheirkhah πŸ‘‹

Software Engineer | Scalable Systems, Machine Learning & Mathematical Optimization

LinkedIn Email Portfolio


πŸ‘¨β€πŸ’» About Me

I am a Computer Engineer (B.Sc.) currently specializing in software architecture at grit:lab in Γ…land. I bridge the gap between high-performance backend systems and complex data analytics. Whether I am architecting event-driven microservices or tuning genetic optimization algorithms, I focus on building robust, scalable solutions.

  • πŸ”­ Currently focusing on: End-to-end data pipelines, NLP, and event-driven microservices (Kafka/Spring Boot).
  • 🌱 Deepening my knowledge in: Quantitative finance, probabilistic matrix factorization, and Snowflake data warehousing.
  • ⚑ Fun fact: I built a multi-objective optimization model using the NSGA-II algorithm to solve real-world crisis evacuation routing.

πŸ› οΈ Tech Stack & Tools

Languages & Core Math

Data Science, ML & Optimization

Backend & Architecture

Databases & Data Warehousing


πŸš€ Featured Work

  • πŸ•΅οΈ NLP News Scraper & Risk Intelligence: Automated NLP pipeline transforming raw RSS feeds into actionable Risk Intelligence using Snowflake, LinearSVC, and GloVe embeddings.
  • 🎬 Matrix Factorization Recommender System: Built an enterprise-grade movie recommendation engine utilizing SVD and PMF to learn latent user preferences from highly sparse datasets.
  • 🚒 Titanic Survival Prediction: A robust machine learning pipeline emphasizing advanced feature engineering, data leakage prevention, and soft-voting ensemble classifiers.
  • πŸ›’ buy-01: Architected a scalable, event-driven e-commerce backend using Java, Spring Boot, Eureka, and Kafka.

πŸ“Š GitHub Analytics


Pinned Loading

  1. sp500-strategies sp500-strategies Public

    A quantitative trading pipeline using Machine Learning to outperform the S&P 500. Features time-series cross-validation, out-of-fold signal generation, and risk-managed backtesting.

    Python

  2. credit-scoring credit-scoring Public

    Econometric ML model for credit risk auditing, featuring a custom Double-Tree piecewise architecture for full transparency, deployed as a serverless Dash application on GCP.

    HTML

  3. Matrix-Factorization Matrix-Factorization Public

    Matrix factorization recommender system utilizing SVD and PMF for collaborative filtering. Features deep interpretability of latent factors on highly sparse datasets, anti-overfitting techniques, a…

    Jupyter Notebook

  4. vision-track vision-track Public

    A production-grade pipeline for real-time person detection, unique identity tracking, and foot-traffic analytics. Built with fine-tuned YOLO, BoT-SORT, ONNX, and Streamlit for ultra-fast local edge…

    Jupyter Notebook

  5. Multi-Objective-Location-Allocation-NSGA-II Multi-Objective-Location-Allocation-NSGA-II Public

    Optimized model with NSGA-II in Python, tuning hyperparameters via genetic algorithms for efficient real-world crisis mapping.

    Jupyter Notebook

  6. buy-01 buy-01 Public

    Architected and developed a microservices-based e-commerce platform using Java, Spring Boot, and MongoDB on the backend and Angular for the frontend. Implemented Eureka for service discovery, Kafka…

    Java 2 2