Browse Prior Art Database

A Method and System for Automation of Product Bundling Service by Scalable Complementary Products Discovery

IP.com Disclosure Number: IPCOM000239857D
Publication Date: 2014-Dec-05
Document File: 2 page(s) / 31K

Publishing Venue

The IP.com Prior Art Database

Related People

Ann Chen: INVENTOR [+2]

Abstract

A method and system is disclosed for suggesting complementary product bundles to a user while shopping on an e-commerce website. The method and system leverages the users' behavior as well as taxonomy information such as, but not limited to “buy-also-buy” model and “view-also-view” model to group complementary products.

This text was extracted from a Microsoft Word document.
This is the abbreviated version, containing approximately 53% of the total text.

A Method and System for Automation of Product Bundling Service by Scalable Complementary Products Discovery

Abstract

A method and system is disclosed for suggesting complementary product bundles to a user while shopping on an e-commerce website.  The method and system leverages the users' behavior as well as taxonomy information such as, but not limited to “buy-also-buy” model and “view-also-view” model to group complementary products.

Description

Traditionally, product recommendation systems surface up complementary products that could be bundled together according to “view-also-view” and
“buy-also-buy models”.  Although the notion of “products bought together" somewhat reflects that the products are complementary, the coverage is quite low due to the scarcity of buying events.  Moreover, “view-also-view” products with high relevancy mostly are similar products, not complementary ones.  Additionally, it is often easy to identify complementary product taxonomies, for example, clothes and shoes.  However, it is difficult to automatically identify the matching products in terms of attributes that do not have a clear definition such as, but not limited to style, and contrast.

Disclosed is a method and system for suggesting complementary product bundles to a user while shopping on an e-commerce website.  

The method and system utilizes a product catalog tree to identify complementary product bundles.  The product catalog tree is a hierarchical structure that describes the relationship between different product groups.  The products belonging to the same node in the product catalog tree are often listed together on the e-commerce website.  The characteristic of this tree is that most products belonging to the same node will be similar in terms of functionalities and style.

The method and system allows the seller to specify pairs of nodes in which the products are complementary.  For example, the seller can specify the product catalog tree nodes A and B representing dresses and shoes respectively as complementary nodes.  It is not sufficient to enumerate all products in node A along with node B as complementary products since their styles may not match well.

Subsequently, the method and system utilizes “view-also-view” model to filter the candidates with...