Obelix Searches Internet Using Customer Data

O ne major problem with purchasing through the Web is locating reliable suppliers that offer the exact product or service you need. In the usual approach, you access an indexing-based search engine, specify keywords for the purchase, and initiate the search. The outcome is typically a list ranked according to keyword matches—useful, but not always helpful. Keyword matches provide only one ingredient to finding the right Web sites. The ranking should also consider the satisfaction of previous customers purchasing from those sites, customer profiles, and customer behavior. The Obelix search engine uses recon-figurable technology to apply customer satisfaction data obtained from the Internet service provider infrastructure to refine its search criteria. The Obelix system collects data about customer activities, calculates a customer satisfaction index, and updates the search engines with its findings. Consider the following scenario: An ISP advertises that it has the appropriate infrastructure to collect customer satisfaction data, process it, and make it available to search and ranking engines used by potential customers. Companies offering high-quality products or services readily buy their Internet access from this provider, because taking advantage of the satisfaction of past customers makes sense for such companies. The browser implements the customer satisfaction specifiers. Developers modify the browser so that it can collect data about clicks to select a page, cache a page, purchase from a page, and so on. Since many successful browsers (such as Netscape) are now public domain, this is not a problem. Even privately owned companies such as Microsoft will likely permit ISPs to upgrade their proprietary browsers if customers demand these customer satisfaction specifiers. The modified browser collects this data for every Web site hosted at the ISP. A clock records the time of each purchase so that the related statistical analysis can include time. In addition, the analysis weighs the data. For example, selection gets one point; caching, two points; the first purchase, four points; and so on. If the second purchase follows quickly enough after the first or if the density of purchases increases (both signs of a good product or service and high customer satisfaction), follow-up purchases get eight or more points. We can extend this scenario to include customer profiles that provide even more information for a search engine to use in refining its searches. When customers first visit an e-commerce site, they answer certain profile-related questions. A search engine uses this information to affect …