Portrait of an Online Shopper: Understanding and Predicting Consumer Behavior
By Farshad Kooti, Kristina Lerman, Luca Maria Aiello, Mihajlo Grbovic, Nemanja Djuric, Vladan Radosavljevic. 2015
82 citations recorded by the source corpus.
Consumer spending accounts for a large fraction of economic footprint of modern countries. Increasingly, consumer activity is moving to the web, where digital receipts of online purchases provide valuable data sources detailing consumer behavior. We consider such data extracted from emails and combined with with consumers' demographic information, which we use to characterize, model, and predict purchasing behavior. We analyze such behavior of consumers in different age and gender groups, and find interesting, actionable patterns that can be used to improve ad targeting systems. For example, we found that the amount of money spent on online purchases grows sharply with age, peaking in the late 30s, while shoppers from wealthy areas tend to purchase more expensive items and buy them more frequently. Furthermore, we look at the influence of social connections on purchasing habits, as well as at the temporal dynamics of online shopping where we discovered daily and weekly behavioral patterns. Finally, we build a model to predict when shoppers are most likely to make a purchase and how much will they spend, showing improvement over baseline approaches. The presented results paint a clear picture of a modern online shopper, and allow better understanding of consumer behavior that can help improve marketing efforts and make shopping more pleasant and efficient experience for online customers.
Subfields: Marketing, Sociology and Political Science, Transportation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Marketing
In Sociology and Political Science
In Transportation
Citations in the corpus
- Computational social scientist beware: Simpson’s paradox in behavioral data (2017, background): “The study looked at the relationship between purchase price of an item and the time interval since last purchase [13].”
- Information is not a Virus, and Other Consequences of Human Cognitive Limits (2016, background): “When studying social systems, one needs to isolate the more homogeneous populations and carry out analysis within each population [38].”