DP

Hi! I'm Divya. I turn complex data into actionable insights with SQL, Python, Tableau, and Snowflake. Two years of experience analyzing user behavior, measuring chatbot performance, and automating reporting.

Available for full-time data analyst opportunities

Years of Experience
2Years of Experience
Transactions Analyzed
30M+Transactions Analyzed
Less Reporting Time
30%Less Reporting Time

// about

I’m a Data Analyst with two years of experience connecting complex datasets to business decisions. At Prodapt Solutions, I analyzed conversational AI interactions to understand where users dropped off and help teams improve self-service experiences.

My background includes an M.S. in Information Systems from Northeastern University (May 2026) and a B.E. in Information Science from Jyothy Institute of Technology (June 2021). My work spans statistical analysis, data modeling, automated reporting, and machine learning.

role
Data Analyst
based
United States
mobility
Open to relocate
toolkit
SQL, Python, Tableau, Snowflake
focus
User behavior & conversational AI analytics

// work experience

  1. Oct 2021 – Aug 2023

    Data Analyst

    Prodapt Solutions · India

    • Analyzed customer service chatbot logs in Snowflake with SQL and Python to identify user drop-off trends and inform product changes.0% user abandonment
    • Designed Tableau dashboards tracking intent recognition accuracy, escalation rate, session duration, and self-service resolution for product and engineering teams.
    • Partnered with product and engineering teams on A/B testing and statistical analysis to validate a new chatbot prompt structure.+0% self-service resolution
    • Automated daily chatbot telemetry pipelines in Snowflake using dbt, transforming raw interactions into analytics-ready datasets.0% manual reporting turnaround
    • Maintained dbt models and SQL transformations in GitHub, documenting data sources and dependencies to improve data quality, governance, and lineage.
  2. Mar 2021 – Apr 2021

    Machine Learning Intern

    Tech Fortune Technologies · India

    • Built wine-quality classifiers across 1,599 samples using Python and scikit-learn, comparing Random Forest, SVM, KNN, Decision Tree, and Logistic Regression.0% test accuracy
    • Engineered an ML pipeline with StandardScaler, GridSearchCV, cross-validation, and an 80/20 train-test split to prevent data leakage and improve generalization.0 .5% cross-validation accuracy
    • Explored feature relationships and class imbalance with Pandas, Matplotlib, and Seaborn, restructuring the target into a binary classification problem.

// projects

3 selected projects
  1. 01

    E-Commerce Customer Behavior & Product Demand Analytics — view source on GitHub (opens in a new tab)

    Purchasing patterns, customer segments, and product demand insights from 30M+ e-commerce transactions.

    0.84 ROC-AUC with Random Forest

    Used EDA, RFM segmentation, and K-Means clustering to support retention and marketing. Compared Logistic Regression, Decision Tree, and Random Forest models to inform inventory and demand planning.

    • Python
    • Pandas
    • NumPy
    • scikit-learn
    • RFM
    • K-Means
  2. 02

    Secure AI Governance Engine — view source on GitHub (opens in a new tab)

    A RAG-powered compliance reasoning system with 100% citation groundedness and 91%+ accuracy.

    80% reduction in prompt token usage

    Combined document chunking, embeddings, and vector search with ReAct agent workflows. Validated the system with 28 unit tests and 5 integration tests.

    • Python
    • GPT-4o
    • LangChain
    • LangGraph
    • ChromaDB
    • Docker
    • RAG
  3. 03

    Cloud Native Webapp — view source on GitHub (opens in a new tab)

    A scalable Python backend with automated AWS infrastructure and zero-downtime deployments.

    Integrated FastAPI and REST APIs with AWS services including S3, RDS, and CloudWatch. Automated infrastructure and deployments with Terraform, Packer-built AMIs, and GitHub Actions, with encryption and centralized logging.

    • Python
    • FastAPI
    • AWS
    • Terraform
    • Packer
    • GitHub Actions

// skills

analytics toolkit

Languages & Databases

  • Python
  • SQL
  • R
  • PostgreSQL
  • MySQL
  • Oracle
  • MongoDB
  • PL/SQL
  • Excel

Analysis & Machine Learning

  • Pandas
  • NumPy
  • scikit-learn
  • Jupyter Notebooks
  • EDA
  • A/B Testing
  • Statistical Analysis
  • Data Modeling

Visualization & Reporting

  • Tableau
  • Power BI
  • Matplotlib
  • Seaborn
  • KPI Dashboards
  • Automated Reporting

Cloud Platforms

  • Snowflake
  • AWS EC2
  • AWS S3
  • AWS Lambda
  • Azure

Pipelines & Orchestration

  • dbt
  • Airflow
  • Docker
  • FastAPI

Tools & Collaboration

  • Git
  • GitHub
  • Jira
  • Data Quality
  • Data Lineage

// contact

Divya Prakash · United States · Open to relocateback to top ↑