Recent advancements in smartphone-embedded GPS and accelerometer sensors have enabled the detailed measurement of consumer outing behaviors. These data are increasingly utilized across various fields, such as healthcare, gaming, and marketing, contributing to the digital transformation of service industries. However, the relationship between individual characteristics, including age, interests, and attitudes, and observed movement patterns remains poorly understood. A deeper understanding of the latent lifestyle dimensions underlying individual characteristics is essential for designing sustainable, human-centered services that address diverse consumer needs and preferences. In this study, we investigate how individual lifestyle factors relate to outing behavior. We obtained and analyzed one month outing behavior data, including GPS locations and transportation modes, from approximately 3,000 users. These data were supplemented with questionnaire responses regarding lifestyle preferences. Through exploratory factor analysis of the questionnaire data, we identified five key lifestyle factors representing underlying dimensions of consumer preferences. We then built models to predict the strength of each factor using both mobility patterns (e.g., weekend activities) and self-reported preferences (e.g., travel interest) as predictors. This integrative modeling approach enabled us to link subjective lifestyle traits with observed behaviors. The results demonstrate that the strength of lifestyle factors can be accurately predicted (mean ROC-AUC = 0.77) by integrating smartphone-based mobility data with self-reported outing preferences. This finding highlights the potential of an integrative modeling approach of observed behavior to enhance customer understanding, which is a critical component in delivering superior services in the service industry.