Read an article in Science Daily (Understanding urban issues through credit cards) that talked about a study published in Nature (Sequences of purchases in credit card data reveals lifestyles of urban populations) that applies big data to B2C marketing.
The researchers examined call data records (CDRs), credit card transactions records (CCRs) and demographic (age, sex, residential zip code, wage level, etc.) data and did a cross table between them to identify sequences of purchases. They then used these sequences to identify different lifestyle groups in the urban area.
The analyzed data from Mexico City, Mexico. The CCR data was collected for 10 weeks across 150K users. The had CDR data for 1/10th of the users for 6 months surrounding the 10 weeks duration. Credit card adoption is still low in Mexico (18%), so the analysis may be biased. When thy matched CCR expenditures against median wages in a district and they found their participants came from higher wage populations. Their data also spanned all districts within the city.
The analysis identified sequences of purchase categories as well as expenditures. They characterized purchase sequences as “words”.
Using the word data and further statistical analysis they were able to split the population up into 5 distinct lifestyle groups.
The loops of icons above represent major purchase categories derived from the CCR data merchant category codes (MCC). Each of the rings in “a” above show the same 12 major MCC purchase categories. If you look at each ring, one can identify a central or core node that seems to have the most incoming or outgoing arks. These seem to be the central purchases made by that lifestyle group after which they branch out to other purchase categories.
There are five different lifestyle categories (they also show the city average) delineated in the data:
- Commuter – generally they have to pay tolls, have longer travel between home and work and have a diverse sequence of purchase that occurs after purchases from the toll category.
- Household – purchases seem to center on grocery stores/supermarkets and then branch off from there.
- Young – purchases seem to center on the taxicab category and then go to computer-networking, restaurants, grocery stores/supermarkets.
- Hi-Tech – purchases seem to center on computer-networking, then go to gas stations, grocery stores/supermarkets, restaurants, and telecomm.
- Average – seems to have two focuses grocery stores/supermarkets and restaurants and then goes out from there to gas stations, specialty food stores and department stores.
- Dinner-out – purchases seem to center on restaurants and then branch out fro there to computer-networking, gas stations, supermarkets, fast food, etc.
In “b” breakout above, you can see the socio-demographic characteristics of each lifestyle group as compared with the median user. And in “c” one can see some population histograms of the demographic data.
They were then able to use the CDR data to construct a map of which lifestyle called which other life style to identify call correlation data. Most calls were contacts between the same groups but the second most active call was calls to householders.
They took this same analysis to another city in Mexico and came up with six lifestyle categories, five of the same and a different one.
When I went to Uni (a long long time ago), I attended an urban geography class that was much more scientific and mathematical than any other geography class I had ever attended. I remember asking the professor when did geography become an exact science. As best as I can recall, he laughed and said over the last decade.
Analysis like the above could make B2C marketing, almost an exact science.
Big Data meet Marketing – Buyer beware.
Photo Credit(s): All charts/photos are from the Nature article Sequences of purchase in credit card data reveal lifestyles in urban populations