Byung-Chull Bae

Inferring the true demand for a product or a service from aggregate data is often challenging due to the limited available supply, thus resulting in observations that are censored and correspond to the realized demand, thereby not accounting for the unsatisfied demand. Censored regression models are able to account for the effect of censoring due to the limited supply, but they don't consider the effect of substitutions, which may cause the demand for similar alternative products or services to increase. This paper proposes Diffusion-aware Censored Demand Models, which combine a Tobit likelihood with a graph-based diffusion process in order to model the latent process of transfer of unsatisfied demand between similar products or services. We instantiate this new class of models under the framework of GPs and, based on both simulated and real-world data for modeling sales, bike-sharing demand, and EV charging demand, demonstrate its ability to better recover the true demand and produce more accurate out-of-sample predictions.

A virtual reality (VR) environment is different from the generally produced video-based experience, as it creates an interactive user experience (UX) by allowing the users to respond to operations or commands using various input devices. In particular, as existing analog-type fashion shows that have limitations in space and time have evolved into digital fashion shows that include interaction, the importance of the naturalness of interaction and visual expression is being emphasized in UX research. However, study cases that maximize user immersion through the interaction of visual changes in the stage and clothes of a digital fashion show are scarce. As such, this study introduces an interactive VR fashion show to analyze the impact of interaction on the UX in a VR environment. In the design of the interactive VR fashion show, various interaction elements that affect the UX are selected and the scope of UX application is suggested. In addition, by utilizing a commercial game engine, the production process necessary to simulate an existing fashion show is shown step-by-step. The user test in this study is examined in-depth by dividing the evaluation of the user into a two-step survey, and the results are objectively verified through a statistical analysis.