Project Portfolio

Data Science & Analytics Solutions

Explore my journey through data science projects, from machine learning implementations to large-scale analytics platforms

Featured Projects

Comprehensive data science solutions across different domains

Research Analytics Platform

Built a comprehensive analytics platform at University of Rochester to process 800GB+ of research data, enhancing data-driven hiring decisions and institutional impact assessments.

BigQuery dbt Dash Tableau Python
  • Processed 800GB+ of institutional data for strategic decision-making
  • Increased research focus and media coverage by 20% through interactive dashboards
  • Implemented dbt for efficient data transformation and documentation
  • Built peer benchmarking dashboards for institutional strategy

Risk Strategy Simulation Tool

Engineered an automated risk analysis tool at T-Mobile that revolutionized credit risk management processes, boosting team productivity by 40% and reducing investigation time by 75%.

Python Pandas Snowflake Databricks Risk Modeling
  • Automated risk strategy simulations boosting productivity by 40%
  • Built RCA-inclusive alerts reducing investigation time by 75%
  • Analyzed 35% policy deviation patterns using advanced analytics
  • Migrated critical SAS pipeline to Python for better scalability

XGBoost Credit Risk Models

Implemented machine learning-based credit risk models at RedCarpetUp achieving 40% month-over-month growth in credit disbursals and identifying ₹5.2M in revenue opportunities.

XGBoost A/B Testing PostgreSQL Looker Airflow
  • Led cross-functional teams achieving 40% MoM credit growth
  • Implemented XGBoost models with A/B testing across 4,000+ customers
  • Conducted EDA on 5TB customer data identifying ₹5.2M opportunities
  • Optimized reporting efficiency by 65% using Looker and Airflow

Expansive Insights: Developer ChatGPT Analysis

Capstone project analyzing 107,000 developer interactions with ChatGPT to understand GenAI's impact on developer productivity, identifying distinct interaction patterns and usage behaviors.

Python NLP Statistical Analysis Data Mining Pandas
  • Processed 107,000 developer interactions with advanced filtering
  • Identified 16 single-turn and 8 multi-turn interaction types
  • Applied statistical methods to analyze productivity patterns
  • Provided insights into GenAI adoption in software development

Mini-GPT: Transformer Implementation

Built a Transformer-based language model from scratch using PyTorch, implementing attention mechanisms and training on the Tiny Shakespeare dataset for character-level text generation.

PyTorch Transformers Deep Learning NLP Neural Networks
  • Implemented transformer architecture from first principles
  • Built multi-head attention and positional encoding layers
  • Trained on Shakespeare corpus for text generation
  • Achieved coherent character-level language modeling

Enterprise CRM System

Designed and built a comprehensive Customer Relationship Management system at RedCarpetUp serving 500,000+ users with advanced data management and analytics capabilities.

Flask PostgreSQL Python REST APIs Data Engineering
  • Built scalable CRM system for 500,000+ users
  • Designed data pipelines for customer lifecycle management
  • Implemented card upgrade process for 100,000 monthly users
  • Ensured regulatory compliance for financial operations

Technical Expertise

Core technologies and methodologies used across projects

AI & Machine Learning

Large Language Models (LLMs) Generative AI Deep Learning Statistical Modeling A/B Testing MLOps

Data Analytics

Exploratory Data Analysis Statistical Modeling Data Visualization Business Intelligence Credit Risk Modeling

Cloud & Big Data

BigQuery Snowflake Databricks AWS (SageMaker, S3, Lambda) Google Cloud Platform Apache Spark

Data Engineering

dbt Apache Airflow ETL/ELT Pipelines PostgreSQL Data Pipelines Docker

Research & Publications

Peer-to-peer Knowledge Sharing Platform for Farmers

Published research on developing an intelligent recommendation system for agricultural knowledge sharing, enabling farmers to access relevant information and best practices.

Recommendation Systems Machine Learning Agricultural Tech Knowledge Management
  • Published: IEEE SmartTechCon 2017
  • DOI: 10.1109/SmartTechCon.2017.8358498
  • Developed auto-recommendation feature for agricultural knowledge
  • Created peer-to-peer learning platform for farmer communities
View Publication

Impact & Results

Quantifiable outcomes from data science initiatives

Business Growth

Revenue & Efficiency Gains

40% Growth
  • 40% month-over-month credit disbursal growth at RedCarpetUp
  • ₹5.2M in identified revenue opportunities through data analysis
  • 65% improvement in data analysis efficiency

Operational Excellence

Productivity & Process Optimization

75% Reduction
  • 40% boost in team productivity through automation at T-Mobile
  • 75% reduction in investigation time via intelligent alerts
  • 20% increase in research focus and media coverage

Scale & Performance

Data Processing & User Impact

800GB+
  • 800GB+ data processing for research analytics platform
  • 500,000+ users served by CRM system
  • 107,000+ developer interactions analyzed for AI research

Let's Build Something Amazing

Interested in collaborating on your next data science project? Let's discuss how these experiences can drive innovation for your organization.

Start a Conversation View Full Experience