Skip to content
View sultanalikhan7543's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report sultanalikhan7543

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.

Content in all repositories owned by your account will be closed.
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
sultanalikhan7543/README.md

🧠 About Me

I'm a Data Scientist & Machine Learning Engineer from Upper Chitral, Pakistan. I build LLM-integrated systems, research interpretable conversational AI, and validate financial ML pipelines on synthetic data before making real-world claims.

  • 🔬 Currently working on: Modular context-gathering architectures for reliable multi-domain LLM generation
  • 🎓 Preparing for: Graduate research in AI/ML abroad
  • 💡 Interested in: Interpretability, applied NLP, computer vision, robotics, and intelligent systems
  • 🌐 Portfolio: sultanalikhan7543.github.io/Portfolio

🛠️ Tech Stack

Languages & Tools

AI / ML & Data Science

Robotics & Reinforcement Learning

Web & Platforms


📊 GitHub Stats

GitHub Streak

🐍 Contribution Snake

Snake animation

🚀 Featured Projects

A conversational AI platform that asks clarifying questions before returning ranked results. 9-tool suite with Claude API.

Claude API JavaScript HTML/CSS

Marketing analytics dashboard that turns campaign data into plain-English insight.

Python Streamlit Claude API

Applied ML project identifying fraudulent transactions from highly imbalanced data.

scikit-learn Pandas Classification

Synthetic order-flow-imbalance pipeline validation study with LightGBM.

Python LightGBM Synthetic data

Privacy-preserving ECG arrhythmia classification under non-IID data distributions.

PyTorch Federated Learning Research

Benchmark of recurrent vs. memoryless policies for mobile robot navigation.

Reinforcement Learning PyTorch Robotics


📝 Latest Publications

  • Federated Learning for Privacy-Preserving ECG Arrhythmia Classification — Zenodo, Oct 2026 · Read →
  • Temporal Memory for Robust Navigation under Distribution Shift — Zenodo, Oct 2026 · Read →

💬 Let's connect

Portfolio · LinkedIn · Google Scholar · Email


Profile views

Pinned Loading

  1. adlytix-ai adlytix-ai Public

    A context-gathering conversational AI platform built with the Claude API. Features a 9-tool suite for search, SOP writing, CV building, and career planning.

    Python 1

  2. Flux-research Flux-research Public

    A standalone, independently verified synthetic order-flow-imbalance pipeline validation study for financial ML using LightGBM and synthetic data.

    Python 1

  3. Meridian Meridian Public

    A context-gathering conversational AI platform built with the Claude API. Features a 9-tool suite for search, SOP writing, CV building, and career planning.

    Python 1

  4. federated-ecg-research federated-ecg-research Public

    Federated learning for privacy-preserving ECG arrhythmia classification under non-IID data distributions

    Python 1

  5. sim2real-navigation sim2real-navigation Public

    Controlled benchmark comparing memoryless MLP and recurrent LSTM policies for mobile robot navigation under distribution shift. Includes code, trained models, and paper.

    Python 1

  6. Portfolio Portfolio Public

    A modern 3D portfolio with voice intro, interactive research map, and dual themes. Built with GSAP, Three.js, and vanilla JS.

    HTML 1