Currently an Extern @Pfizer

Data Analytics Professional Ready to Innovate

I'm a data analytics expert leveraging AI to drive insights and efficiency. Let's transform data into action together!

Work samples

Dive into my portfolio showcasing AI-driven projects, including document intelligence solutions that automate real-world workflows.

  • DATA ANALYST
    DATA ANALYST

    Developed a predictive modeling pipeline on 50,882 customer records to analyze insurance offer response behavior, performing data cleaning, feature engineering, and multi-model comparison to support customer segmentation. Developed an NLP-based sentiment analysis model to classify customer reviews and identify opinion trends, uncovering key insights such as a strong positive correlation between review length and helpfulness to inform product and service improvement strategies.

  • Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
    Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship
    Pfizer logo

    Pfizer · ✅ Verified by Extern · ⏱️ In progress

    Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

    Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.

    AI & MLPythonDocument IntelligencePresentation Skills

About me

I'm a data analytics expert leveraging AI to drive insights and efficiency. Let's transform data into action together!

I am a data analytics professional with a master's degree, reentering the workforce after a career break. My focus is on strengthening my resume and enhancing my competitiveness in the job market.

Externships

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

Pfizer

Experience

SENIOR DATA ANALYST

Star Health and Allied Insurance India · Feb 2020 - Oct 2022

Transportation Data Specialist

Amazon Development Centre India · Aug 2016 - Aug 2017

Education

Springboard Data Science and Machine Learning Bootcamp

Class of 2024

PGP (Data Science and Machine Learning), Great Lakes Institute of Management

Class of 2020

MTech (Biotechnology), Jawaharlal Nehru Technological University

Class of 2019

Skills

Data AnalyticsAI-Powered SolutionsOCRDocument IntelligenceLarge Language ModelsWorkflow Automation

DATA ANALYST

Developed a predictive modeling pipeline on 50,882 customer records to analyze insurance offer response behavior, performing data cleaning, feature engineering, and multi-model comparison to support customer segmentation. Developed an NLP-based sentiment analysis model to classify customer reviews and identify opinion trends, uncovering key insights such as a strong positive correlation between review length and helpfulness to inform product and service improvement strategies.

View all works

✅ Verified by Extern · ⏱️ In progress

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.

AI & MLPythonDocument IntelligencePresentation Skills

Overview

The externship prototyped AI document-intelligence workflows that combined OCR, embedding-based retrieval, and large language models to process enterprise PDFs. Work included research, architecture sketches, and hands-on pipelines assembled for document ingestion, indexing, and question-answering. Deliverables documented methods and prototype components.

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

What I've accomplished

I inspected real vendor documents and documented specific data-quality issues—such as inconsistent date formats, repeated boilerplate, merged or multi-line table cells, and checkbox-style forms—that interfere with OCR and automated extraction.

Project breakdown

I inspected sample vendor documents, noted inconsistent date formats, repeated boilerplate, merged/multi-line table cells, and checkbox-style forms. I described how each issue could hinder OCR and automated data extraction.

View all works