Author
Listed:
- Ling-Yi Chou
(National Chung Cheng University, Taiwan)
- Shi-Ming Huang
(National Chung Cheng University, Taiwan)
- I-Heng Wu
(Asus, Taiwan)
Abstract
With increasing popularity of e-commerce, the growth potential of this business is extraordinary; however, the main challenge for such a paradigm originates from the difficult in finding the most valuable products to recommend customer appropriate information. One of the problems is that business managers generally lack sufficient information to identify whether the product descriptions and images in the website successfully attracted customers in browsing and buying the products. The objective of this research is to develop a recommendation mechanism using multimedia data mining algorithm. Basically, it analyses a large amount of multimedia images information to find the most valuable images and descriptions of products. Our findings show that these images and descriptions match customers' various demands. This paper use the color image semantics applied in the Munsell (HSV) color space and use the content-based image retrieval application to establish a recommendation rule based on an associative classification method for various product images in ecommerce. The prototype has been developed to evaluate the mechanism feasibility and is applied in a real e-commerce case. The result shows that it is useful for on-line sellers to make recommendation decisions. In order to further validate the practicability of this mechanism, the extensive case study with larger trading volumes in apparel e-business areas was conducted. This case study shows that the multimedia data mining approach is an automatic and effective solution, which can be used in marketing to discover consumer habits.
Suggested Citation
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:tkp:mklp14:1239-1247. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Maks Jezovnik (email available below). General contact details of provider: http://www.toknowpress.net/proceedings/978-961-6914-09-3/ .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.