Vending-Machine-Analytics 

This project focused on analyzing vending machine transaction data to uncover insights into product performance, machine usage, and sales trends across different locations. The analysis aimed to help optimize product stocking, improve machine profitability, and enhance customer satisfaction. 

LINK TO PROJECT

Roles Played in Project

• Imported and cleaned transaction data using Pandas to ensure data quality and consistency.

• Conducted exploratory data analysis (EDA) with Pandas and NumPy to summarize key metrics such as total sales, machine performance, and product categories.

• Created visualizations using Matplotlib and Seaborn to display sales trends, top-selling products, and machine utilization across locations.

• Applied grouping and aggregation techniques to identify best-selling items and high-performing vending machines.

• Derived actionable insights to guide recommendations on stock management and machine deployment.

Key Observations

• Machines located in high-traffic areas recorded significantly higher sales than those in less accessible locations.

• Snack and beverage categories accounted for the majority of total sales across all machines.

• Several products showed consistently low sales volume, indicating overstocking or low customer interest.

• Peak sales periods were observed during lunch hours and weekends, suggesting time-based customer purchase patterns.

Recommendations

• Relocate low-performing machines to areas with higher customer traffic to maximize revenue.

• Streamline inventory by focusing on fast-moving products and discontinuing underperforming items.

• Adjust restocking schedules dynamically based on sales data to reduce stockouts and overstocking.

• Introduce targeted promotions or combo offers during identified peak sales times to drive additional sales.