Logo: University of Southern California

What Do Target Shoppers Want?

Just ask researchers in the USC Data Science Lab, first place winners in the Target Data Challenge.
By: Natalia VĂ©lez
May 11, 2016 —

The digital age has made an unprecedented volume of information available to marketers. From search histories to click-rates, e-commerce businesses can potentially know everything about users’ online profiles, and they are constantly looking for ways to gain insights that will translate to higher sales.

With this in mind, the USC Viterbi Institute for Innovation, in collaboration with the Target Corporation, recently hosted the Target Data Challenge, a competition in which over 20 teams used a dataset of Target customers’ transactions and product descriptions to predict their future purchases.

A team of researchers from the USC Data Science Laboratory won first place in the April 15 competition, along with an award of $10,000, for coming up with an algorithm that improves customer product recommendations. The victorious team consisted of USC Viterbi computer science Ph.D. students Chung Ming Cheung, Palash Goyal and Ajitesh Srivastava and was mentored by research associate Arash Saber Tehrani, all members of Professor Viktor Prasanna’s Data Science Lab.

A team of researchers from the USC Data Science Lab has won the first place in the Target Data Challenge.
From left to right: Chung Ming Cheung (PhD student), Arash Saber Tehrani (post-doctoral research associate), Palash Goyal (PhD student), and Ajitesh Srivastava (PhD student).
Image provided by Professor Arash Saber Tehrani

"I am thrilled to hear about this award,” Professor Prasanna said. “My Data Science Lab has been looking into applications of machine learning in smart oil field and smart grid, and the Target challenge problem is a new application direction that complements our ongoing work."

From the initial 20 competitors, only four teams reached the semi-final round. The semi-finalists competed against each other at the Viterbi Hacker House on April 15, and the Data Science Lab team was selected as winner, based on three criteria: prediction results, presentation and novelty.

The team’s approach was based on formalism for social network analysis using multi-level representation, random walks, and random sampling, which allowed them to discover patterns of relatedness that mediate transactions.

"Not everything went smoothly,” said Ph.D. student Chung Ming Cheung. “We tried many approaches and most did not give good results, but we were thrilled when our predictive model finally appeared to make good predictions."

Recommender systems are nothing new. In fact, companies like Amazon and Netflix have used them for a while to increase sales. Nevertheless, these systems are still flawed, and it is not uncommon for them to make suggestions that are far from accurate.

“Current recommender systems fail to pinpoint exactly what users are looking for,” said Tehrani. “However, I do think that what we did is a small step towards reaching a perfect system.”