acm-header
Sign In

Communications of the ACM

ACM TechNews

'Hooking' Online Shoppers Is About More Than Popularity


A happy woman shopping.

The researchers found customer engagement rose by as much as 30% when rankings were determined through a dynamic blend of product popularity and variety among products.

Credit: arvigbusiness.com

A team of researchers from Canada's University of Toronto, the Harvard Business School, and home goods online retailer Wayfair designed algorithms to engage more online shoppers by ranking items using a combination of popularity and variety.

The researchers concentrated on hedonic browsing, in which shoppers casually check out sites for attractive items, and retailers must "hook" them to continue browsing.

The algorithms help Wayfair's Website ascertain and continually tweak the set of product rankings for any given shopping event.

The programs hooked an average 5% to 30% more customers than an algorithm based on popularity alone across six events, and they can learn to formulate the best product mix without requiring massive volumes of data.

From University of Toronto Rotman School of Management (Canada)
View Full Article

 

Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA


 

No entries found