Supermarket Sales Analysis (Python)

📌 Business Context

The rapid growth of supermarkets in highly populated cities has increased market competition.
Understanding sales behavior, customer ratings, and revenue drivers is key to improving decision-making across branches.

This project analyzes historical supermarket sales data from three branches over a three-month period to identify patterns and generate actionable insights.

🎯 Objective

• Analyze sales performance across branches
• Evaluate customer ratings and their relationship with revenue
• Explore gross income behavior over time
• Identify relationships between key variables

📊 Dataset

• Source: Kaggle – Supermarket Sales Dataset
  https://www.kaggle.com/datasets/aungpyaeap/supermarket-sales
• Period: 3 months (2019)
• Branches: 3
• Key variables: branch, customer rating, gross income, gender, date

🛠️ Methodology

The analysis was conducted using Python in a Jupyter Notebook and included:

• Data inspection and validation
• Handling duplicated and missing values
• Univariate analysis (distribution of key variables)
• Bivariate analysis (relationships between customer rating, gross income, branch and gender)
• Time-based analysis of gross income
• Correlation analysis across numeric variables

📈 Exploratory Analysis

Univariate Analysis

• Customer rating shows a uniform distribution
• Sales volume is similar across all branches

Bivariate Analysis

• No clear relationship between customer rating and gross income
• Gross income shows little variation by branch or gender
• A sales peak was observed on February 15, 2019, but no consistent time trend

Correlation Analysis

A correlation heatmap was used to evaluate relationships among numeric variables.

💡 Key Insights

• Customer ratings are evenly distributed and do not significantly influence spending
• Branch location does not affect transaction volume or gross income
• Gross income is not strongly influenced by gender or branch
• No strong correlations were found between customer rating and other variables

🧰 Tools & Technologies

• Python
• Pandas, NumPy
• Matplotlib, Seaborn
• Jupyter Notebook

🚀 Next Steps

• Build a predictive model for gross income
• Segment customers based on purchasing behavior
• Create an interactive dashboard for business users