Survey on Hybrid Critiquing

groupFun-homepage Given their respective strengths, a Hybrid of Example-Critiquing (EC) and Dynamic-Critiquing (DC) was developed to combine them together on the same screen, so that users can not only specify their own critiques if necessary with EC, but also obtain the knowledge of remaining recommendation opportunities and pick the suggested critiques by DC if one of them matches their desires.

Online Product Finder


The system has been developed to assist users in searching for high-involvement products, such as digital cameras, tablet PCs, and laptops. It is composed of two main decision components: preference-based organization interface and example-critiquing support.
The former acts as explanation facility to help users understand the computational reasoning of recommendation generation but also critiques suggestions to guide users to make informed tradeoff navigations. The user is further supported to freely refine her/his preferences with the latter, by which s/he could choose a product to be critiqued and determine how to critique it, such as improving some of its feature on behalf of less important attributes. It gives users high level of control over the process of preference revision and feedback provision.
Run this demo, More about this project.

CritiqueShop – Critique-based Recommender Systems

groupFun-homepage CritiqueShop is an online platform for designing and evaluating e-commerce product search tools based on the critiquing technique. It provides a unified user interface so that the performances of different recommendation algorithms can be evaluated under the same condition. This system is developed with Java/AJAX (see Google web toolkit for the detail of this technology). For more information about this system, please see our publications.

Example-Critiquing Interface for Apartment Search

groupFun-homepage A crucial element in consumer electronic commerce is a catalog tool that not only finds the product for the user, but also convinces him that he has made the best choice.
We have examined the performance of such tools on a variety of tasks involving selection and tradeoff. The studies clearly show that example-based search is comparable to ranked lists on simple tasks, but significantly reduces the error rate and search time when complex tradeoffs are involved. This shows that such tools are likely to be useful particularly for extending the scope of consumer e-commerce to more complex products.

Vacation Planning System

groupFun-homepage We have developed and implemented an online vacation planning prototype that helps users in the vacation packages selection process. Two algorithms were implemented, one for finding packages that satisfy user requirements, the other one for computing the list of values that the user can further select for each of the vacation attributes. Easy-to-understand visualizations are used for displaying the vacation attributes and the resulting vacation packages.

SmartClient Travel Planning System

groupFun-homepage Travel products are complex, involving combining flights, car rental, and hotels. Applying our technology developed for general electronic catalogs, we have successfully implemented a travel planning system, enabling customers to view a large selection of flights, search specific trips using their personal criteria, and plan their trips integrating car rentals and hotel accommodations.