PIYUSH SUTHAR

Skilled data professional with expertise in data analysis, statical modeling and business intelligence using tools like SQL, Excel, Python and Power BI. Undergraduate in Artificial Intelligence and Data Science with hands on exposure to data visualization, predictive analytics. Eager to contribute to data-driven roles in analytics and data science while continuously advancing my skills in machine learning and AI.

Programming in Python(U-M)

• Currently following a structured 7-step Data Analyst Roadmap, including:
  Excel & Data Manipulation
  Python for Data Analysis
  SQL for Data Handling
  Exploratory Data Analysis (EDA)
  Data Cleaning & Wrangling
  Machine Learning Basics
  Dashboarding & Reporting
• Gaining hands-on experience with tools like:
  Pandas, NumPy, Matplotlib, Seaborn
  MySQL, Excel, Power BI/Tableau
  Jupyter Notebook, Google Colab

• Exploring final-year project ideas like:
  Breast Cancer Prediction Model using ML classification techniques.
  A Social Media Analytics Dashboard, helping businesses track engagement, reach, and growth metrics.
  An interior/home organization web app combining analytics with user needs.

• Practicing Python, SQL, and basic statistics regularly to improve problem-solving.
• Exploring platforms like LeetCode for logic building and interviews.
• Able to write clean code for data pipelines, conditional logic, and ETL tasks.

• Preparing for internships and entry-level Data Analyst roles.
• Already comfortable with core responsibilities like:
  Data cleaning and preprocessing
  Visualizing trends
  Drawing business insights from raw data

• Build a data-driven portfolio with real-world business problems.
• Land a remote or hybrid analyst role to grow while pursuing freelancing in parallel.
• Eventually combine data + content for marketing analytics, helping brands make smart creative decisions.

This project helps businesses understand which vendors or brands are performing best by analyzing sales, purchases, freight, and profits using SQL and Python.

• Imports CSVs to SQLite DB
• Generates a summary of vendor-wise metrics
• Cleans and transforms data
• Performs EDA to find insights like:Top vendors by sales
  Brands with high margin but low sales
  Inventory turnover & locked capital
  Statistical differences in vendor performance
  

• Python (pandas, seaborn, matplotlib, scipy)
• SQLite + SQLAlchemy
• Logging

• Vendor selection
• Promotional targeting
• Inventory management
• Capital optimization