📍 Karachi, Pakistan · Open to Remote

Ayyan Khan

Data Analyst Python Developer ML Engineer

→ LinkedIn ⌥ GitHub ✉ Email

Repositories

GitHub Stars

Churn Accuracy

~/ayyan-khan — zsh

ayyan@dev:~ python profile.py

# Loading Ayyan Khan v2.0...

✓ "Turning raw data into actionable insights"

✓ Currently: RL Trading Bot & Financial NLP Analysis

✓ Learning: Deep Learning, NLP, Time Series

✓ Status: Available for opportunities

ayyan@dev:~

About

Background

I'm a Data Analyst & ML Engineer pursuing a Bachelor's in Data Science. As a freelance analyst, I specialize in transforming complex datasets into compelling visual stories that drive decisions.

Current Focus

Reinforcement Learning Trading Bot with DQN variants
Financial News Sentiment Analysis (NLP + Transformers)
Advanced Time Series Forecasting techniques
Deepening expertise in PyTorch & Deep Learning

Tech Stack

Languages & Core

🐍Python 🗄️SQL ⚙️C++

Data & Visualization

🐼Pandas 🔢NumPy 📊Matplotlib 🌊Seaborn 📈Plotly ☀️Apache Superset

Machine Learning & AI

🤖Scikit-learn 🧠TensorFlow 🔥PyTorch 💬NLTK / Transformers 📉Deep Q-Networks

Tools & Platforms

📓Jupyter 🌿Git 📋Excel 🚀Streamlit

Featured Projects

🎓 ↗

Student Digital Life vs Academic Results

Comprehensive analysis of 15,000 student records correlating digital device usage, sleep patterns, and study habits with academic performance. Full EDA + Streamlit dashboard.

EDA Streamlit 15k Records Mar 2026

🏗️ ↗

Housing Price MLOps Pipeline

Production-ready ML pipeline for housing price prediction with MLflow experiment tracking, DVC data versioning, and an interactive Streamlit dashboard. End-to-end ML engineering.

MLflow DVC Streamlit MLOps

🎵 ↗

Music Popularity Analysis

Deep dive into what makes a song popular — full data cleaning, EDA, feature correlation, and predictive modeling on a large music dataset with rich visualizations.

EDA Pandas Seaborn Prediction

🤖 ↗

AI Task Analysis & Predictive Modeling

Multi-technique analysis of AI tasks using EDA, NLP, clustering, and classification. Categorizes tasks and predicts task types from text descriptions — Apache 2.0 licensed.

NLP Clustering Classification Apache 2.0

📉 ↗

Customer Churn Prediction

Predicts customer churn with 90%+ accuracy using ML models. Includes an interactive Streamlit web app for real-time analysis and a full Jupyter notebook covering model development.

90% Accuracy Streamlit Sklearn Classification

🌍 ↗

Global AI Content Impact Analysis

Interactive analysis and dashboard for the Global AI Content Impact Dataset — exploring AI adoption trends, economic effects, and social impacts across industries worldwide.

AI Trends Dashboard EDA Global Data

Experience & Education

🎓

Bachelor's in Data Science

Currently enrolled · Data Science & Analytics focus · Academic projects in ML, NLP & Statistical Modeling

💼

Freelance Data Analyst

Remote & flexible engagements · Client dashboards, predictive models, data pipelines · Global clientele

🏅

Open Source Contributor

52+ public repositories · 59+ GitHub stars · Active in Python & ML community · Streamlit deployments

// let's collaborate

Open to Opportunities

Data Analysis · ML Engineering · Business Intelligence · Freelance Projects