ABOUT ME
Profile Picture

Suparna Chowdhury

Data Scientist

LinkedIn

I translate complex data into actionable insights, driving tangible business results. My expertise in machine learning, predictive modeling, and NLP empowers teams to make smarter, faster, data-driven decisions.

Whether it is building robust models in Python or crafting clear dashboards in Tableau, I bring a mix of technical depth and strategic focus — always aligning solutions with customer needs.

When I am not working with data, I enjoy playing the piano to relax and recharge. Known for blending adaptability with code (and the occasional chord), I am a collaborative problem-solver who transforms noise into clarity.

EDUCATION
University of South Alabama Logo

MS in Electrical Engineering

University of South Alabama, Alabama • July 2015

PUBLICATIONS

A reinforcement learning algorithm based technique for thermal energy management of a PEM fuel cell power plant

IEEE • December 2017

Efficient face recognition using local derivative pattern and shifted phase-encoded fringe-adjusted joint transform correlation

SPIE · April 2016

CERTIFICATIONS
IBM Data Science Professional Certificate

IBM Data Science Professional Certificate

IBM • January 2023

Fundamentals of Visualization with Tableau

Fundamentals of Visualization with Tableau

IBM • January 2023

Areas of Interest

Machine Learning

Machine learning is a tool, not a buzzword—I love optimizing algorithms and solving real business problems.

Natural Language Processing

With NLP, I extract insights from messy text and turn human language into structured knowledge.

Data Visualization

Data speaks louder when visualized—I enjoy designing charts that drive decisions.

Statistical Analysis

I use statistical techniques to validate assumptions and guide decision-making with confidence.

SQL Database

SQL is my tool for organizing data, running efficient queries, and making sense of massive datasets.

Data Preprocessing

I treat data preprocessing as an art—refining raw data into clean, efficient structures for efficient analysis.

Machines That Learn: Projects Showcase

Credit Default Risk Analysis for Nova Bank

I applied Random Forest and XGBoost to credit risk data to uncover how borrower traits, loan details, and credit history influence default risk across the USA, UK, and Canada.

Click to Conversion: Tracking Paid User Behavior

This project analyzes user behavior before purchase by mapping paid users’ session journeys using SQL views and event tracking data.

Truth or Trick: Deep Learning for Fake News Detection

This project builds a fake news detection model using LSTM-based deep learning and GloVe word embeddings to classify news articles as real or fake.

Analytics in Action

A SQL Project on Retail Sales, Retention, and Cohort Analysis

SQL project analyzing Superstore data to reveal retention, cohort trends, and discount impact for better decisions.

Click to Conversion: A SQL Project on Tracking Paid User Behavior

This project analyzes user behavior before purchase by mapping paid users’ session journeys using SQL views and event tracking data.

Retail Sales, Target Achievement & Customer Behavior Analysis

This project uses SQL to analyze sales performance, customer behavior, and sales target trends from retail transactional data