Mobile User Preference Mining And Analysis

Nowadays，mobile internet and communication technology rapid development,economic globalization, prompting the development of electronic commerce derived anew development direction, namely mobile e-commerce. Unlike traditionale-commerce, mobile e-commerce has diversified characteristics, namely the diversityof mobile, data, personalized features, these features also determines the mobilee-commerce on service economy bring the huge benefits. On the other hand, theservice economy is driving the development of mobile e-commerce, service economyprompted the mobile e-commerce on precise marketing, comparison shopping andreal-time optimization distribution put forward the urgent request, is also theimportant opportunity of development.The characteristics of mobile e-commerce is mainly manifested in the user’smobility characteristics and dependence on the surrounding environment. The moremobility of mobile e-business reflects its characteristics of convenience, namely, canat anytime, anywhere through a variety of mobile terminal for business activities. Italso determines the user’s demand will changes with the change of the surroundingenvironment. Therefore, the demand for user access and analysis, namely the study ofuser interest degree is particularly important. How in the vast, disorderly usersbusiness information quickly and efficiently get interested in mobile users ofinformation, in order to provide high quality service, is the main direction of thisarticle are to study.This article first to understanding of mobile electronic business background,through summary analysis of the characteristics of mobile e-commerce, includingmobile environment and the mobile users, that is, from the two aspects of subjectiveand objective analysis. Secondly, in this paper, the data mining and association rulemining method for the study and research, literature related to the association rulesmining method in the field of electronic commerce application user preference mining analysis methods are summarized and the research, through the summary and analysisof the classic methods, find out shortage, on the basis of optimization and rich, toimprove the efficiency of user preference mining. Finally, for the traditional algorithmand improved algorithm are compared and experimental verification, through theexperiment of two kinds of algorithm design and result analysis, in order to verify theimproved algorithm is superior to the traditional algorithm, at the same time allowthem to better adapt to in the mobile e-business environment of rapid excavation andanalysis of the mobile user preferences. Thus, for the mobile e-commerce businesssuch as precision marketing, comparison shopping on the better solution.