|
Title:
|
DIGICAM: A NEED-BASED RECOMMENDER SYSTEM |
|
Author(s):
|
Ai Thanh Ho , Esma Aïmeur |
|
ISBN:
|
972-8924-23-2 |
|
Editors:
|
Sandeep Krishnamurthy and Pedro Isaías |
|
Year:
|
2006 |
|
Edition:
|
Single |
|
Keywords:
|
Recommender system, web-based e-commerce. |
|
Type:
|
Full Paper |
|
First Page:
|
73 |
|
Last Page:
|
80 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
In web-based e-commerce and online shopping, one of the most important problems is the selection problem. It corresponds to the user looking for a product of a certain type, with uncertainty in the details of the request. This task is quite difficult for most common users with little technical knowledge, and it is particularly challenging for novice users. As novice users have no expectations about the ranges of offered products, they need good explanations of the recommendations to be convinced to buy a product. In other words, they need to establish trust and rapport with a recommender system before taking advantage of its recommendations. This paper presents the DiGiCam Recommender System as a solution for these challenges. The objective of DiGiCam is to provide adapted and personalized suggestions to novice users who do not have much technical knowledge about digital cameras and do not know how to specify their needs in terms of product features. Products are recommended based on inferences about a users needs and preferences, as well as opinions of other similar users. Our system uses a combination of collaborative filtering, knowledge-based technique, and utility-based technique. We discuss the system design and implementation, as well as its performance evaluation. Our results indicate that our system attains higher precision and is easier to use for novice users than traditional feature-based recommendations. |
|
|
|
|
|
|
