The Instacart stakeholders are interested in the variety of customers in their database along with their purchasing behaviors to inform their targeted marketing strategy.
The final project here
The analysis was done using four data sets that included information about customers, products, and orders.
-
Python
-
Excel
-
Data Cleaning: Improved data quality by eliminating duplicates, rectifying missing values, and ensuring data types were consistent.
-
Merging Datasets: Prepared and curated datasets for effective merging, validated the success of data merges, and archived the final merge in a pkl file format.
-
Exploratory Analysis: Unearthed insights through comprehensive exploratory analysis, encompassing essential descriptive statistics, and data distribution visualizations.
-
Data Transformation: Created novel variables by grouping data based on user, order, and department, enabling in-depth exploration and analysis at different levels. Validated the integrity of newly derived data using crosstabs and value counts.
-
Data Visualization: Leveraged Matplotlib and Seaborn libraries to craft visually compelling representations, including histograms, scatterplots, line charts, pie charts, and various bar chart configurations (vertical, horizontal, stacked, and 100% stacked).
-
Reporting: Delivered valuable insights through an Excel report that not only addressed inquiries from the sales and marketing teams but also documented the entire data processing workflow. This documentation covered data population statistics, data consistency checks, data transformation, the creation of new columns to ensure transparency and reproducibility, and visualizations.