Cyndi Kohashi
- Instacart -
An online grocery delivery or pick-up service.
Objective
The goal of this project is to uncover customer purchasing patterns, which can be used for a targeted marketing strategy.
This includes looking at days and times with the most orders, brand loyalty of the customer base, regional differences, and differences between customer demographics.
Data
- Data is the Instacart Online Grocery Shopping Dataset 2017, accessed from https://www.instacart.com/datasets/grocery-shopping-2017 via Kaggle on Nov 15th, 2023.
- Customer data and prices were created for educational purposes
- Data dictionary was provided
- Project brief
Skills
- Data cleaning, wrangling, subsetting, and merging
- Data consistency checks
- Deriving new variables
- Grouping and aggregating data with Python
- Visualization with Python
- Creating population flow and reporting in Excel
Tools
- Microsoft Excel
- Anaconda
- Jupyter Notebook
- Python
- Python libraries Pandas, NumPy, Seaborn, Matplotlib, and SciPy
Customer Ordering Habits
Busiest Day
The days of the week with the most orders are Saturday (0.0) and Sunday (1.0).
Busiest Hour
The time of day with the most orders is 10 AM - 4 PM (hour 10-16). The most money spent, however, is at 1 AM and 4 AM.
Brand Loyalty
49% of all customers are considered Regular Customers (have 10 to 40 max orders). Regular Customers also make up 60% of Non-Frequent Customers (an average of 20 days since their last order).
Loyal Customers (over 40 max orders) make up 56% of all Frequent Customers (average of 10 days or less since their last order).
Departments
The departments with the most orders are Produce, Dairy & Eggs, Snacks, Beverages, and Frozen.
Produce makes up 29% of all orders.
Regions
33% of all customers are in the South region, followed by West (26%), Midwest (23%), and Northeast (18%).
While the South region has the largest customer base, spending habits appear to be the same among all regions.
All regions have around 32% of Loyal Customers and 49% of Regular Customers.
Customer Profiles
Based on age, family status, and number of dependants we can break down the customer base into different demographic categories.
The largest demographic base is comprised of those age 33-64 who are married with dependants.
The largest customer base also primarily buys from the produce department, and makes up the most customers in the South region.
In fact, all groups make up the same ratio across all regions and departments.
An example would be the Babies department, which has purchases from all groups regardless of the number of dependants.
Conclusion & Recommendations
Popular Order Times
The busiest times are weekends from 10AM-4PM. To increase traffic during slow times, ads should be run on the weekdays before 10AM and after 4PM.
Promotions & Deals
Starting a price match program for in-store prices can increase customer frequency. The current loyalty program is based on delivery drivers. A customer based one can also increase loyalty.
Regions & Family Status
Focus advertising on the largest part of the customer base, the South Region and those married of any age and dependants.
Departments & Products
Promote produce, dairy/eggs, snacks, beverages, and frozen department products. These are the most popular departments.
© 2019