Create your free profile

About

Data professional experienced across the analytics-to-ML pipeline: SQL/Python for data extraction and cleaning, Power BI/Tableau for dashboards, and Scikit-learn/NLTK for predictive and NLP models. Reduced manual reporting effort by 25% and data processing time by 30% via automation.

Experience2

  1. Research Analyst

    Apr 2026 — Jul 2026

    Markscan

    Investigated and tracked unauthorized distribution of copyrighted content across third-party websites, verifying URLs and compiling structured evidence reports. Prepared documentation used to support content takedown requests, working within defined turnaround-time targets.

  2. Data Mining & Analyst (Jr. Executive)

    Dec 2025 — Mar 2026

    Usedon Computer India Pvt. Ltd.

    Engineered 5+ EDA pipelines in Python (Pandas) on sales datasets, surfacing KPI insights that informed business decisions. Partnered with 3 analysts to design and maintain Power BI dashboards tracking 10+ business KPIs on a weekly cadence. Optimized SQL queries and Pandas preprocessing scripts, cutting data processing time by 30% across 50K+ records. Automated weekly reporting workflows using Python and BeautifulSoup web scraping, reducing manual analyst effort by 25% and freeing 8 hrs/week.

Projects3

  • Scam Mail Prediction — NLP Spam Classifier

    Built and deployed an NLP-based spam classifier in Scikit-learn, achieving 94% accuracy on 5K+ email samples. Implemented TF-IDF vectorization with a tuned Naive Bayes classifier, improving F1-score from 88% to 94% on held-out test data. Collaborated with 2 peers to refine the NLP preprocessing pipeline, cutting training time by 20% via batch processing.

    • Scikit-learn

  • Blinkit Sales Analysis — BI Dashboard

    Built an interactive Power BI dashboard tracking 8+ KPIs for delivery performance metrics. Designed 3 DAX-based data models, improving query accuracy by 20% and reducing dashboard load time. Transformed 10K+ raw sales records using SQL and Excel Pivot Tables, improving report accuracy by 18%.

    • Power BI
    • SQL
    • Excel

  • Uber Trip Data Analysis — Python/EDA

    Analyzed 500K+ Uber trip records with Python/Pandas, identifying peak demand zones and usage patterns; built 10+ Matplotlib/Seaborn visualizations of trip-duration and surge-pricing trends. Cleaned raw trip data with Pandas, reducing null values by 35% to enable reliable downstream analysis.

    • Python
    • Pandas
    • Matplotlib
    • Seaborn

Education3

  • Data Science Program

    2024 — 2025

    Prepleaf by Masai

  • Bachelor of Commerce (B.Com)

    2020 — 2023

    Mahatma Jyotiba Phule Rohilkhand University

  • Diploma

    2020 — 2024

    Govt. Polytechnic Rampur

    Computer Science