Mobile Product Browsing using Bayesian Retrieval
Reacting to technological advances in the domain of mobile devic devices, many traditionally es, desktop desktop-bound applications now are ready to mak make the transition into the mobile world. e Especially mob mobile shopping applications promise a large ile potential for commercial commercial. However,. in order to work on the limited screen estate even of mod modern devices, ern traditional category category-based brow brows-sing approaches to online shop ing shopping have to be rethought. In this ping paper we design an innovative approach to intuitively guide users through product database databases based on Bayesian probability mode model-ling ing for navigational purposes. Our navigation model is focused on feedback and inspired by content content-based retrieval techniques techniques. Moreover, we exploit new features of today’s devices like touch screens t to ease interaction o interaction. Due to th the novel interface interface-related simplicity, our system supports users in their decision process while demanding only minimal cognitive load load. We outline the theoretical foundations and the design sp space of such a sy ace system and stem evaluate its retrieval effectiveness using real real-world data sets. In fact fact, we show that using our probabilistic navigation model about 98％ of all searches can be completed successfully with an ave averrage of only 3 age rounds of feedback on the 4 th display displayed screen ed screen.
mobile e-commerce commerce mobile interfaces interfaces probabilistic retrieval
Christoph Lofi Christian Nieke Wolf Wolf-Tilo Balke
Institute for Information Systems Technische Universit(a)t Braunschweig Braunschweig, Germany
国际会议
上海
英文
96-103
2010-11-10（万方平台首次上网日期，不代表论文的发表时间）