π This project presents an end-to-end Exploratory Data Analysis (EDA) on Diwali Sales data with the goal of uncovering actionable business insights for targeted marketing and strategic decision-making. Using Python and core data analysis libraries, the dataset is analyzed to identify key customer segments, spending behaviors, and state-wise revenue distribution during the Diwali festival season. This analysis supports real-world use cases like campaign optimization and customer profiling.
Simulating the role of a junior data analyst at a retail company using Diwali sales data to:
- π― Discover high-revenue customer segments
- π§ Recommend marketing strategies based on customer behavior
- π Support business decisions using data insights
| Tool | Purpose |
|---|---|
| Python (Jupyter Notebook) | Analysis environment |
| Pandas, NumPy | Data manipulation & preprocessing |
| Matplotlib, Seaborn | Visualization |
| Power BI (optional) | Business dashboarding |
- Source: Diwali Sales (fictional dataset)
- Rows: 11,251
- Columns: 15
- Features: Gender, Age Group, Marital Status, Occupation, State, Product Category, Amount, etc.
- βοΈ Removed null and missing values
- βοΈ Dropped non-relevant columns like
Status,Unnamed - βοΈ Standardized and cleaned categorical variables
- βοΈ Converted data types as required
- π©βπ¦° Females made more purchases (by count)
- π¨ Males spent more in total amount
- π₯ Age group 26β35 dominates in both count and spending
- π― Ideal demographic for campaign targeting
- π₯ Top States: Uttar Pradesh, Maharashtra, Karnataka
- π High demand zones for future campaigns
- π Married individuals contributed more to total revenue
- ποΈ Family-centric spending patterns
- πΌ Working professionals spent the most
- π¦ Popular categories: Electronics, Clothing
- π― Target Segment: Married Males, Aged 26β35, Working Professionals
- π Focus States: Uttar Pradesh, Maharashtra, Karnataka
- π§Ύ Female customers make frequent purchases but spend less per transaction
- β Launch personalized Diwali marketing campaigns for target segments
- β Focus inventory and advertising efforts in top-performing states
- β Promote high-demand products based on occupational preferences