About Me

As a Data Science professional with an extensive academic background, including my Master of Data Science studies, I specialize in bridging the gap between raw data and executive decision-making.

Beyond traditional machine learning and exploratory data analysis (EDA), I have a keen focus on emergent technologies, including Generative AI, Retrieval-Augmented Generation (RAG), and Cloud Infrastructure (Azure). Whether it's segmenting customer behavior for marketing optimization or building end-to-end predictive pipelines, I deliver robust, scalable solutions.

Python (Pandas, Scikit-learn) Machine Learning & MLOps Generative AI & RAG Time Series Forecasting Statistical Analysis SQL & Data Wrangling Tableau & Power BI Azure Cloud Services
Nabankur Ray, Data Scientist

Freelance Services

Predictive Modeling

Building custom machine learning models (classification, regression, forecasting) to predict customer churn, sales trends, and risk management.

Data Wrangling & Pipelines

Cleaning, transforming, and automating complex datasets from varied sources (APIs, SQL, CSVs) into analysis-ready formats.

Interactive Dashboards

Designing dynamic, stakeholder-friendly visualizations using Tableau and Python to track KPIs and track business performance.

Featured Projects

Generative AI & Intelligent Systems

ShopSmart Recommendation Bot

Multimodal AI-powered e-commerce bot on Azure using OpenAI (GPT), CLU, and AI Search (RAG).

Azure OpenAI RAG Bot SDK

Healthcare Assistant Chatbot

AI-powered chatbot built with Azure Cognitive Services Language Studio for domain-specific Q&A.

Azure AI NLP Custom Q&A

Urban Scene Intelligence

Computer vision pipeline for object detection and tracking using Azure Image Analysis API and OpenCV.

Azure CV OpenCV Deep Learning

Predictive Analytics & Machine Learning

House Price Prediction App

Interactive Streamlit application predicting real estate prices using Random Forest and XGBoost.

Streamlit Deployment XGBoost

Credit Default & Market Risk

Predicts company default risk and analyzes market volatility using machine learning and financial metrics.

Python Machine Learning Finance

Automobile Customer Analytics

Analyzed car sales & customer patterns to derive actionable business strategies and targeted marketing segments.

Python EDA Segmentation

AllLife Bank Segmentation

Clustered customers using K-Means & Hierarchical models for targeted marketing and product optimization.

K-Means Clustering Targeting

Booking Cancellation Prediction

Built predictive models using Logistic Regression, KNN, and Decision Trees to forecast hotel booking cancellations.

Logistic Regression Decision Trees

A/B Testing & Inferential Analysis

Applied ANOVA, Chi-Square & Hypothesis Testing to extract key marketing insights and evaluate portal effectiveness.

A/B Testing ANOVA Statistics

PySpark Business Analytics

End-to-end big data pipeline on 500K+ reviews using PySpark, NLP, and ALS Recommendation System.

PySpark NLP Big Data

Visa Approval Classification

Ensemble ML model predicting U.S. visa outcomes using applicant and employer attributes.

Random Forest XGBoost ML

Cafe Sales & Market Basket

Analyzed purchase patterns and menu optimization using Python (EDA) and KNIME analytics.

Python KNIME Market Basket

Operations Research & Optimization

Linear programming models in R for resource allocation and zero-sum strategic decision-making.

R Optimization Game Theory

Wine Sales Forecasting

Time-series analysis and forecasting for ABC Estate Wines using ARIMA and decomposition methods.

Time Series ARIMA Python

BCCI Cricket Win Prediction

Capstone project predicting match outcomes for the Indian cricket team using historical data.

Machine Learning EDA Python

Residential Energy Modelling

Predictive modelling of appliance energy consumption using advanced aggregation functions in R.

R Energy Modelling EDA

Business Intelligence & Visualization

Car Insurance Claims Dashboard

Interactive Tableau dashboard analyzing car insurance claim patterns, risk trends, and regional demographics.

Tableau Dashboarding Data Viz

FIFA 2018 Performance Insights

Visual analytics dashboard tracking player performance metrics, wages, and team statistics.

Power BI Sports Analytics BI-Dashboarding

Consolidated Portfolios & Coursework

ML Project Portfolio (SIG720)

Six end-to-end projects showcasing expertise in clustering, classification, and regression.

Supervised Unsupervised Deep Learning

Data Wrangling Portfolio (SIG731)

Consolidated repository showcasing advanced data wrangling, text mining, and statistical modeling.

Data Cleaning Regex NLP

Python Problem Solving

Collection of Python problems covering DSA, string manipulation, and data science simulations.

Algorithms DSA Monte Carlo

Credentials & Certifications

GL PGP Certificate

PGP in Data Science & Business Analytics (Great Lakes)

UT Austin PGP Certificate

PGP in Data Science and Business Analytics (UT Austin)

View Credential
Accenture Analytics Certificate

Accenture Data Analytics & Visualization

Verified
Generative AI Certificate

Generative AI Course

View Credential
Big Data Analytics Certificate

Mastering Big Data Analytics

View Credential
Power BI Certificate

Data Visualization using PowerBI

View Credential
RAG Certificate

End-to-end RAG Application Development with LangChain and Streamlit

Verified

Articles & Insights

Women in Tech

Why aren’t there more women in data science?

Exploring the diversity gap in the tech industry and data fields.

Read Article
World Data

How to change the world with data science?

Using data for social good and impactful decision making.

Read Article