Building reliable machine learning systems with mathematics, statistics, and data.

I'm currently pursuing an M.Sc. in Mathematics at NIT Kurukshetra, where I specialize in applying mathematical thinking to practical machine learning problems.

My interests lie at the intersection of:

• 🤖 Machine Learning
• 📊 Data Science
• 📈 Bayesian Statistics
• 🧠 Explainable AI
• ⚙️ MLOps
• 💹 Quantitative Finance (long-term)

I enjoy building end-to-end ML systems—from data preprocessing and model development to deployment and monitoring.

• End-to-end ML pipeline
• XGBoost classifier
• SHAP explainability
• FastAPI REST API
• Docker deployment
• MLflow experiment tracking

A production-ready framework for Bayesian online experimentation that compares Frequentist and Bayesian approaches to A/B testing.

Highlights

• Bayesian inference using Beta-Binomial conjugate models
• Monte Carlo simulation for decision making
• Sequential experiment updates
• Business metrics (Expected Loss, Expected Uplift, Probability to Beat Control)
• Interactive Streamlit dashboard
• Modular Python package with reusable components

Tech Stack

Python • NumPy • SciPy • Plotly • Streamlit • Bayesian Statistics

GitHub Repository

Live Demo

• Time Series Forecasting
• Recommendation Systems
• MLOps Pipelines
• Deep Learning
• NLP

• Deep Learning
• MLOps
• Production ML Systems
• SQL Interview Preparation

• ✅ Master SQL for Data Science interviews
• ✅ Strengthen MLOps fundamentals
• ✅ Contribute to open source
• ✅ Secure a Machine Learning/Data Science internship
• ✅ Publish technical blogs documenting project learnings

• 🚀 Building production-ready Machine Learning projects
• 📚 Currently learning Deep Learning, MLOps & Production ML Systems
• 💡 Regularly practicing SQL and Data Structures
• 🔬 Exploring Explainable AI and Quantitative Finance

• 💼 LinkedIn: https://www.linkedin.com/in/abhishek-goswami-07b340231/

"Strong mathematical foundations. Practical machine learning. Continuous improvement."