Instacart is a platform that offers online grocery delivery and pickup, allowing customers to shop from local stores and have their orders either delivered to their doorstep or prepared for in-store pickup.
The goal of this project is to perform an initial exploratory data analysis (EDA) to derive actionable insights from Instacart’s customer and order data. These insights will help the marketing and sales teams optimize advertising strategies, customer segmentation, and promotional targeting.
- Analyze shopping patterns to identify the busiest times and days of the week for order placement.
- Determine peak spending hours to tailor product promotions based on customer spending behavior.
- Create simplified price range groupings to better categorize products and guide pricing strategies.
- Identify popular product categories or departments based on order frequency.
- Understand customer behavior across various demographics (e.g., age, income, family size, gender).
- Investigate customer loyalty patterns to understand what factors influence repeat usage.
- Segment customers into distinct profiles based on behavioral and demographic traits.
- What are the busiest days of the week and hours of the day for orders?
→ To schedule ads during lower-traffic periods. - At what times of day do customers spend the most money?
→ To align high-value product promotions with peak spending periods. - How can products be grouped into simpler price ranges?
→ To streamline marketing efforts based on price sensitivity. - Which product categories or departments are most frequently ordered?
→ To highlight popular products in advertising. - How do order frequencies differ by demographic variables such as:
- Age group
- Gender
- Income level
- Family size
- What factors influence brand loyalty?
→ For example: order frequency, product preferences, or demographic traits. - How do different customer profiles behave?
→ Analyze order value, product types, ordering frequency, and more.
• Project management : Project berief and related documents
• Data : Original data and cleaned Prepared data for analysis (Not uploaded due to size limitation)
• Scripts : Python code used to answer key questions
• Analysis : contains all graphics used for exploratory analysis and insight explanation.
• Sent to client : Final Excel presentation
• Pandas
• Numpy
• OS
• Matplotib
• Seaborn
1).“The Instacart Online Grocery Shopping Dataset 2017" Accessed from www.instacart.com/datasets/grocery-shopping-2017 via Kaggle on <March-24th 2025>.
2). Customer data provided by Career foundry
(Customer data and prices column in the Products data are fabricated for the purpose of learning)