Data Scientist
& ML Engineer
Premium data analytics, machine learning, and AI
solutions to help your business stand out.
Premium data analytics, machine learning, and AI
solutions to help your business stand out.
From predictive models to interactive dashboards — here are the projects that define my journey.
Real-time sentiment analysis of Twitter data using NLP and BERT, deployed as an interactive Streamlit dashboard with live visualizations.
LSTM-based neural network predicting stock prices with 94% directional accuracy. Features interactive charts and backtesting engine.
End-to-end ML pipeline predicting customer churn with XGBoost. Includes automated feature engineering, SHAP explanations, and Flask API.
Hybrid recommendation system combining collaborative filtering and content-based methods. Serves 10K+ recommendations via REST API.
Real-time sentiment analysis of Twitter data using NLP and BERT, deployed as an interactive Streamlit dashboard with live visualizations.
LSTM-based neural network predicting stock prices with 94% directional accuracy. Features interactive charts and backtesting engine.
End-to-end ML pipeline predicting customer churn with XGBoost. Includes automated feature engineering, SHAP explanations, and Flask API.
Hybrid recommendation system combining collaborative filtering and content-based methods. Serves 10K+ recommendations via REST API.
A versatile toolkit for every stage of the data science lifecycle.
I'm passionate about uncovering patterns in complex datasets and building intelligent systems that solve real-world problems.
I'm Durvankur, a Data Science student with a deep curiosity for how data shapes the world around us. My journey started with a simple question — "Can we predict the future from patterns in the past?" — and has since evolved into a full-stack data science skill set.
I specialize in building end-to-end ML pipelines, from exploratory data analysis and feature engineering to model training, evaluation, and deployment. I love working with messy, real-world datasets and transforming them into clear, actionable insights.
When I'm not training models, I'm exploring new research papers, contributing to open-source projects, and competing in Kaggle competitions.
Building predictive models and data pipelines. Working on customer segmentation using clustering algorithms and deploying ML models to production.
Focused coursework in Machine Learning, Statistical Analysis, Data Structures, Linear Algebra, and Probability Theory. Active in ML research groups and hackathons.
Participated in multiple competitions including Titanic, House Prices, and Tabular Playground. Achieved top 10% rankings in prediction challenges.
Contributing to data science libraries and building open-source tools for data preprocessing and model evaluation.