Data Scientist - Information Technology Services, at
Praveen Kumar Ponnugupati portrait

Data science graduate student building practical analytics work

Master's student at the University of Connecticut studying Data Science, combining coursework and hands-on experience to solve real data problems.

Work samples

A portfolio of coursework and practical projects from my master’s program, showing data cleaning, exploratory analysis, modelling, and visualisation work.

  • Student Exam Performance Prediction
    Student Exam Performance Prediction

    Predicted student failure risk by analyzing 20+ features including attendance patterns, assignment completion, and grade trends, achieved 93% accuracy and 96% recall, enabling timely advisor intervention. Handled severe class imbalance (75/25 split) by rebalancing training data and adjusting model thresholds to catch at-risk students the model was initially ignoring. Segmented students into 5 behavioral clusters revealing patterns like attendance decline and assignment gaps that preceded failure but werent captured in grade reports.

  • Grandmaster Chess Coach — CLI AI Agent
    Grandmaster Chess Coach — CLI AI Agent

    Built a local-first AI chess coaching agent that analyzes chess.com games using Stockfish engine evaluation and a locally hosted LLM (Ollama + Qwen 2.5), running entirely on-device with no API costs. Implemented long-term memory (Supermemory) so the agent recalls a player's recurring mistakes and tracks improvement across sessions. Added opponent scouting that analyzes public chess.com archives to generate pre-game preparation reports.

    StockfishOllamaQwen 2.5Supermemory

About me

Master's student at the University of Connecticut studying Data Science, combining coursework and hands-on experience to solve real data problems.

I am Praveen Kumar Ponnugupati, a graduate student in Data Science at the University of Connecticut. I have some work experience and I am completing a master’s degree while refining my skills in data analysis, modelling, and practical problem solving.

Experience

Data Scientist - Information Technology Services, UConn

UConn · Dec 2025 – Present

Technical Lead - Cognizant Technology Solutions (Travelers Insurance)

Cognizant Technology Solutions (Travelers Insurance) · Jan 2022 – Jul 2025

Education

University of Connecticut

Master of Science, Business Analytics and Project Management — Concentration: AI & Machine Learning · Class of 2027

Bharath Institute of Higher Education and Research

Bachelor of Technology, Aerospace Engineering · Class of 2021

Skills

Data analysisStatistical modellingData cleaningData visualizationPythonSQLAIAI Agent DevelopmentAI Powered AnalyticsAI Workflow DesignAI-Driven InsightsAI-Enhanced Design

Student Exam Performance Prediction

Predicted student failure risk by analyzing 20+ features including attendance patterns, assignment completion, and grade trends, achieved 93% accuracy and 96% recall, enabling timely advisor intervention. Handled severe class imbalance (75/25 split) by rebalancing training data and adjusting model thresholds to catch at-risk students the model was initially ignoring. Segmented students into 5 behavioral clusters revealing patterns like attendance decline and assignment gaps that preceded failure but werent captured in grade reports.

View all works

Grandmaster Chess Coach — CLI AI Agent

Built a local-first AI chess coaching agent that analyzes chess.com games using Stockfish engine evaluation and a locally hosted LLM (Ollama + Qwen 2.5), running entirely on-device with no API costs. Implemented long-term memory (Supermemory) so the agent recalls a player's recurring mistakes and tracks improvement across sessions. Added opponent scouting that analyzes public chess.com archives to generate pre-game preparation reports.

StockfishOllamaQwen 2.5Supermemory
View all works