The goal of this project was to attract new customers and increase sales for the client. The result was a 93% increase in conversions.
The first step was to find out what types of people to target and how. This was done by exploring current customer data via the client’s Shopify account. Through purchasing behaviours—particularly the amount each customer spent and the number of purchases made—I ran the K-Means algorithm to see whether or not there were existing clusters.
The data showed that there were four main groups of customers, which I categorized from low to high purchasers.
After clustering, the next step was to look into the profiles and characteristics of each bracket. What were their preferences in terms of products and packages? What enticed a new customer to try the brand for the first time?
While much of the budget and focus were given to the top and most consistent customers, I also looked into ways to possibly improve stickiness with the lower tiers of purchasers.
The analysis was done in two weeks using Python to clean and crunch the numbers, as well as derive other customer aspects that weren’t in the data, such as guessing gender from first names (with some margin of error, of course—more than 80% of the customer base was found to be female). For visualization, I used Tableau.
Following the analysis, the e-mail addresses of the top purchasers were used to deploy Facebook ads that targeted lookalike audiences to find others like them.
I also suggested upselling to mid-tier customers using timely discounts and the product formats and flavours that appealed most to them.