Abstract
A business-to-consumer environment can be developed through software agents (Guan, Zhu, & Maung, 2004; Maes, 1994; Nwana & Ndumu, 1996; Wang, Guan, & Chan, 2002) to satisfy the needs of consumers patronizing online e-commerce or m-commerce stores. This includes intelligent filtering services (Chanan & Yadav, 2000) and product brokering services to understand user’s needs better before alerting users of suitable products according to their preference. We present an approach to capture individual user response towards product attributes including nonquantifiable responses. The proposed solution can capture the user’s specific preference and recommend a list of products from the product database. With the proposed approach, the system can handle any unaccounted attribute that is undefined in the system. The system is able to cater to any unaccounted attribute through a general descriptions field found in most product databases. In addition, the system can adapt to changes in user’s preference.
TopBackground
In e-commerce activities, consumers are confused by the large number of options and varieties of goods available. There is a need to provide on top of the existing filtering and search services (Bierwirth, 2000) an effective piece of software in the form of a product brokering agent to understand their needs and help them in selecting products.
Definitions
A user’s choice in selecting a preferred product is often influenced by the product attributes ranging from price to brand name. This research will classify attributes as accounted, unaccounted, and detected. The same attributes may also be classified as quantifiable or nonquantifiable. Accounted attributes are attributes that the system is specially customized to handle. A system is designed to capture the user’s choice in terms of price and brand name, making them accounted attributes. Unaccounted attributes are not predefined in the system ontology. The system does not know whether an unaccounted attribute represents a product feature. Such attributes merely appear in the product descriptions field of the database. The system will attempt to identify unaccounted attributes that affect the user’s preference and consider them as detected attributes. Thus, detected attributes are unaccounted attributes that are detected to be crucial in affecting the user’s preference.
Quantifiable attributes contain specific numeric values (e.g., memory size) and their values are well defined. Nonquantifiable attributes on the other hand do not have any logical or numeric values, and their valuation could differ from user to user (e.g., brand name). The proposed system defines price and quality of a product in the ontology and considers them to be quantifiable, accounted attributes.
Key Terms in this Chapter
Product Brokering: A broker is a party that mediates between a buyer and a seller.
Software Agent: An abstraction, a program that describes software that acts for a user or other program in a relationship of agency.
Tokenize: The process of converting a sequence of characters into a sequence of tokens or symbols.
Attribute: A quality, feature, or characteristic that some product has.
Accounted Attribute: A quality, feature, or characteristic that is listed in product specifications of a specific product.
E-Commerce: Consists primarily of the distributing, buying, selling, marketing, and servicing of products or services over electronic systems such as the Internet and other computer networks.
Genetic Algorithms: Search technique used in computer science to find approximate solutions to optimization and search problems. Genetic algorithms are a particular class of evolutionary algorithm that uses techniques inspired by evolutionary biology such as inheritance, mutation, natural selection, and recombination (or crossover).
Ontology: Studies being or existence and their basic categories and relationships, to determine what entities and what types of entities exist.
M-commerce: M-commerce, or mobile commerce, stands for electronic commerce made through mobile devices.