Geospatial Data Science for Customer Engagement
Using geolocation data from app users who opted in, I analyzed customer behavior during a shopping mall’s Christmas campaign. With Python, Pandas, Folium, and Mixpanel, I identified highly engaged customers, offered them free parking for three months, and mapped their travel patterns. Most customers traveled an average of 5 km to the mall, with some traveling over 40 km. These insights helped optimize marketing efforts, resulting in 60% of these customers participating in subsequent Mother’s and Valentine’s Day campaigns, spending 27% more than the average participant.
I also analyzed a campaign offering 14,000 appetizer coupons across 13 malls. Using Folium to create heat maps, I visualized where customers were when reserving coupons and their time to visit. The data showed that 42% visited the mall the same day, 14% the next day, and 44% within a week, with an average distance of 4.4 km. These findings informed strategies to better align future campaigns with customer behavior, increasing foot traffic and engagement.
You can read more about this analysis in the Investor Relations report this project was showcased in the Earnings Release 4Q20 (p. 15), 2Q21 (p. 20), 1Q22 (p. 12) [direct link to the PDF].