Instacart Grocery Basket Analysis
Project Overview
This project focuses on analyzing Instacart, a popular online grocery store operating through a mobile app. While Instacart boasts strong sales figures, they seek to gain deeper insights into their customer base and purchasing patterns. The purpose of this analysis is to:
Identify and explore customer segments within the Instacart user base.
Derive insights into customer purchasing behavior.
Develop recommendations for a more effective customer segmentation and marketing strategy.
Data Source
The Instacart Online Grocery Shopping Dataset 2017, Accessed via Kaggle.
Customer data and “prices” column in the products data set were both fabricated for the purpose of the CareerFoundry course.
Tools & Skills
Language: Python (Pandas, NumPy, Seaborn, Matplotlib, and Scipy)
Software: Jupyter Notebooks & Excel
Data Wrangling
Data Analysis & Visualization
Key Questions
What are the peak order times and days?
When do customers tend to spend the most?
How can product price ranges improve marketing strategies?
Which product departments are most popular?
How do customer demographics and behaviors vary in terms of brand loyalty, regional differences, and purchasing patterns?
Analysis Process
1. Identify Business Questions
Identify key business questions to guide data analysis, focusing on project goals and stakeholder needs.
2. Data Wrangling
Transform and organize raw data into a structured format suitable for analysis.
3. Create Population Flow
Map and visualize population movements across multiple datasets for cleaning, combining, and merging.
4. Derive Columns
Generate new data columns from existing data to enhance analysis, providing deeper insights.
5. Analyze Data
Examine data to uncover insights, patterns, and trends, helping to answer key business questions and inform decisions.
6. Make Recommendations
Propose actionable strategies based on data analysis insights, tailored to address specific business goals and challenges.
Python Scripts
The first script checks for mixed data types in each column of a Dataframe. This is achieved by mapping the data type of each element in a column and comparing it with the data type of the first element.
The second script demonstrates how to merge two DataFrames using a common key, in this case, 'product_id'. The third script uses conditional statements with the loc() function to create demographic-based customer profiles.
These scripts collectively ensure data quality, enhance dataset richness, and facilitate targeted demographic analysis, which are foundational steps in effective data analysis. For more Python Scripts , click the button below to view the GitHub repository.
Key Insights
Customer Shopping Patterns
Instacart customers show peak shopping activity on Saturdays and Sundays, with the highest order volumes between 10am and 3pm. Conversely, Tuesdays and Wednesdays experience the least activity.
Sales Distribution & Customer Loyalty
Instacart's top five departments—Produce, Dairy Eggs, Snacks, Beverages, and Frozen—account for 70% of grocery unit sales.
Loyal customers, who constitute 32% of the customer base, significantly drive these sales.
Recommendations
Boost sales by targeting advertising campaigns on weekends, capitalizing on higher customer activity and peak shopping times.
Run ads during the evening hours of 7pm to 9pm to effectively capture customers who are placing orders for delivery the following day, maximizing engagement and potential sales.
Create premade bundles of complementary items, include top-selling categories in navigation menus, and prioritize top-selling categories in search results.
Utilize user purchase history to suggest frequently reordered items, making it quick and easy for customers to add these products to their carts, enhancing their shopping experience and encouraging repeat purchases.