ONLINE E-COMMERCE PRODUCT RECOMMENDER SYSTEM
Abstract : Internet is speeding up and modifying the manner in which daily tasks such as online shopping, paying utility bills, watching new movies, communicating, etc., are accomplished. As an example, in older shopping methods, products were mass produced for a single market and audience but that approach is no longer viable. Markets based on long product and development cycles can no longer survive. To stay competitive, markets need to provide different products and services to different customers with different needs. The shift to online shopping has made it incumbent on producers and retailers to customize for customers' needs while providing more options than were possible before. This, however, poses a problem for customers who must now analyze every offering in order to determine what they actually need and will benefit from. To aid customers in this scenario, we discuss about common recommender systems techniques that have been employed and their associated trade-offs.
? In this paper we review existing e-commerce implementations according to how they are presented to consumers.
? Most of the Web stores we review consider the algorithms they use to be proprietary.
? Many of these algorithms could be used while still presenting the same interface to the user. While digital cash has been used for some applications, it is still not widely accepted. Also, today's delivery services require an address to which merchandise can be shipped.
? It is conceivable that privacy concerns may result in the reemergence of digital cash or "single-use" credit card numbers and the creation of trusted delivery services that accept deliveries to a one-time pseudonym, but these services do not yet exist.
? The lack of confidence is the trend toward consolidation in the industry, which means that using personal information "within the company" may include sharing it with a variety of unexpected sites.
? Scalability in recommender systems includes both very large problem sizes and real-time latency requirements.
? For instance, a recommender system connected to a large Web site must produce each recommendation within a few tens of milliseconds while serving hundreds or thousands of consumers simultaneously.
• In this paper, we research these two challenges together, by studying new and existing algorithms that have the potential to improve both scalability and quality of recommender systems.
• There has been little work on experimental validation of recommender systems against a set of real- world datasets
• The focus of this paper is two-fold. First, we provide a systematic experimental evaluation of dicerent techniques for recommender systems, and second, we present new algorithms that are particularly suited for sparse data sets, such as those that are common in E- commerce applications of recommender technology.
? An analysis of the effectiveness of recommender systems on actual customer data from an e- commerce site.
? A comparison of the performance of several dicerent recommender algorithms, including original collaborative clutering algorithms, algorithms based on dimensionality reduction, and lassi al data mining algorithms.
? A new approach to forming recommendations that has online eÆ ien y advantages versus previously studied algorithms, and that also has quality advantages in the presence of very sparse datasets, such as is common with E-commerce purchase data.
|