The widespread adoption of the Internet and information technologies has changed the nature of many industries through easy collection, analysis, and sharing of information. This transformation of information processing makes rapid response and product customization become the major concerns in marketing and strategic planning. This is particularly significant in the industries that offer digital contents to their clients, such as consulting and news services. Due to the digital nature of their products, fully customized services over the Internet is possible. To customize services, however, a company needs to well understand its customers and consequently provide tailored product/services based on their preference.In this paper, a news recommendation system that allows a news service provider to analyze its customer profile and then produce customized news services is developed. The method determines customer interests from the structure of the news read by a client and the reading time. Once customer profile is constructed, personal news services can be provided by the system. An empirical study using actual news provided by the China Times shows that the recommendation system outperforms the traditional headline news compiled by the news editor in both objective performance indices and customer satisfaction. In addition to news services, this approach can be generalized to other industries and services whose products can be digitized, such as consulting and knowledge management.
BackgroundReducing low-density lipoprotein cholesterol (LDL-C) is associated with reduced risk for major coronary events. Despite statin efficacy, a considerable proportion of statin-treated hypercholesterolemic patients fail to reach therapeutic LDL-C targets as defined by guidelines. This study compared the efficacy of ezetimibe added to ongoing statins with doubling the dose of ongoing statin in a population of Taiwanese patients with hypercholesterolemia.MethodsThis was a randomized, open-label, parallel-group comparison study of ezetimibe 10 mg added to ongoing statin compared with doubling the dose of ongoing statin. Adult Taiwanese hypercholesterolemic patients not at optimal LDL-C levels with previous statin treatment were randomized (N = 83) to ongoing statin + ezetimibe (simvastatin, atorvastatin or pravastatin + ezetimibe at doses of 20/10, 10/10 or 20/10 mg) or doubling the dose of ongoing statin (simvastatin 40 mg, atorvastatin 20 mg or pravastatin 40 mg) for 8 weeks. Percent change in total cholesterol, LDL-C, high-density lipoprotein cholesterol (HDL-C) and triglycerides, and specified safety parameters were assessed at 4 and 8 weeks.ResultsAt 8 weeks, patients treated with statin + ezetimibe experienced significantly greater reductions compared with doubling the statin dose in LDL-C (26.2% vs 17.9%, p = 0.0026) and total cholesterol (20.8% vs 12.2%, p = 0.0003). Percentage of patients achieving treatment goal was greater for statin + ezetimibe (58.6%) vs doubling statin (41.2%), but the difference was not statistically significant (p = 0.1675). The safety and tolerability profiles were similar between treatments.ConclusionEzetimibe added to ongoing statin therapy resulted in significantly greater lipid-lowering compared with doubling the dose of statin in Taiwanese patients with hypercholesterolemia. Studies to assess clinical outcome benefit are ongoing.Trial registrationRegistered at ClinicalTrials.gov: NCT00652327
Discovering user interests is a very important task for providing personalized services in electronic commerce. A popular approach is to develop customer profiles from their browsing behavior. In this paper, we present an approach that analyzes the browsing content and time to determine user interests. An empirical study using actual news provided by the China Times shows that the proposed system outperforms the traditional headline news compiled by the news editor in both objective performance indices and customer satisfaction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.