Skip to content
View Khanamin-XOR's full-sized avatar

Block or report Khanamin-XOR

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
Khanamin-XOR/README.md

Hi, I'm Md Amin 👋

M.Sc. Data Science candidate at Technische Universität Hamburg (graduating April 2027). I build production data + ML systems alongside my studies.

🔭 Currently:

  • Working Student, Data Analytics & Web Development — TU Hamburg, International Affairs · Python automation, Plotly dashboards, Erasmus platform engineering
  • Research Assistant (recently completed) — German Aerospace Center (DLR) · built an ontology-generation pipeline over helicopter S1000D maintenance documents using LangChain + RAG

🧰 Stack: Python · SQL · Pandas · PyTorch · Scikit-learn · FastAPI · Docker · Kubernetes · GitLab CI/CD · LangChain · RAG · Plotly

📍 Based in Hamburg, Germany · 🌐 English (C1) · 🇩🇪 German (A2, improving)

📫 Reach me:

📊 GitHub

Profile views GitHub followers Years

Tech I work with

Python PyTorch TensorFlow scikit-learn Pandas NumPy FastAPI Docker Kubernetes LangChain GitLab CI

Pinned Loading

  1. Text-Classification-API Text-Classification-API Public

    German-language text classifier (TF-IDF + SVM) served as a FastAPI + Docker microservice

    Jupyter Notebook

  2. Microsoft-Malware-Detection Microsoft-Malware-Detection Public

    9-class malware family classifier on the Microsoft Malware Classification Challenge — XGBoost with engineered byte/ASM/bigram/image features, log-loss 0.011

    Jupyter Notebook

  3. Movie-Recommender-Matrix-Factorization Movie-Recommender-Matrix-Factorization Public

    Collaborative-filtering recommender built from scratch — Truncated SVD + SGD-trained bias terms in NumPy, with embedding probing for implicit demographic signal

    Jupyter Notebook

  4. Spoken-Digit-LSTM Spoken-Digit-LSTM Public

    LSTM-based spoken digit (0-9) classifier on the Free Spoken Digit Dataset — controlled 2×2 study of raw waveform vs spectrogram inputs and audio augmentation. Best val F1: 98.83%

    Jupyter Notebook

  5. PCA-From-Scratch PCA-From-Scratch Public

    PCA derived from first principles and implemented from scratch in Python — with companion articles in Analytics Vidhya

    Jupyter Notebook 2

  6. ML-Metrics-From-Scratch ML-Metrics-From-Scratch Public

    Classification and regression metrics implemented from scratch in NumPy — confusion matrix, F1, AUC via threshold sweep, cost-sensitive thresholding, MSE/MAPE/R²

    Jupyter Notebook