Communications of the ACM
Algorithm Has a Hunch About What You'll Buy Next
A good complementary recommender system can save shoppers time and suggest novel products.
Research led by UC Riverside's Negin Entezari, her doctoral advisor Vagelis Papalexakis, and Instacart collaborators brings a methodology called tensor decomposition — used by scientists to find patterns in massive volumes of data — into the world of commerce to recommend complementary products more carefully tailored to customer preferences.
Tensors can be pictured as multi-dimensional cubes and are used to model and analyze data with many different components, called multi-aspect data. Data closely related to other data can be connected in a cube arrangement and related to other cubes to uncover patterns in the data. Products co-purchased in a single transaction can be modeled in the form of a tensor.
The work is described in "Tensor-Based Complementary Product Recommendation," presented at the 2021 IEEE International Conference on Big Data.
"Tensors can be used to represent customers' shopping behaviors," says Entezari, who recently received a doctoral degree in computer science at UC Riverside.
From University of California, Riverside
View Full Article
No entries found