Skip to content

Bush-1bit/Sales-Data-Analysis

Repository files navigation

Sales Data Analysis (R)

This project analyzes retail sales data to understand revenue trends, customer behavior, and product performance across different cities and regions.

Project Overview

  • Cleaned and processed raw transaction data
  • Converted variables into appropriate formats (date, categorical variables)
  • Created new metrics such as revenue, cost, and profit
  • Performed exploratory data analysis (EDA) to identify patterns and trends

Key Insights

  • A small number of products generate a large portion of total revenue (Pareto effect)
  • Major cities like New York, Los Angeles, and Chicago contribute the most revenue
  • Returning customers generate more revenue and profit than new customers
  • Promotions increase sales volume but can reduce profit margins if discounts are too high

Analysis Performed

  • Revenue and profit analysis by product, city, and category
  • Trend analysis over time (monthly and weekly patterns)
  • Correlation analysis between variables (price, quantity, discount)
  • Distribution analysis using histograms and box plots
  • Pareto analysis to identify top-performing products

Tools Used

  • R
  • dplyr
  • ggplot2
  • gt (for tables)
  • ggcorrplot

What I Learned

  • How to clean and structure real-world datasets
  • How to analyze business performance using data
  • How to identify key drivers of revenue and profit
  • How to communicate insights using visualizations

Author

Md Boshirul Azad
Cybersecurity Student

About

Analyzed 2,500 sales transactions using RStudio to identify top products, regional performance, and promo effectiveness. Applied trend and Pareto analysis, then delivered findings through a fully reproducible Quarto report with actionable business recommendations.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors