Investigating Customer Satisfaction Patterns in a Community Livability Context: An Efficiency-Oriented Decision-Making Approach

Abstract

A comprehensive understanding of neighborhood facilities distribution and functions along with residential quality of life satisfaction is a key asset for relating livability management to transportation networks. Due to the simultaneous involvement of varied factors with an individual's perception of livability, this concept is difficult to measure. Therefore, a more objective means of quantifying livability is needed. The service industry has demonstrated the intersection of machine learning classifiers and survey domain knowledge for evaluating users' quality of experiences; however, this process of inquiry-based learning has never been considered for solving the communication difficulties between community stakeholders and transportation agencies. Another area of overlap is that of urban computing, which integrates computing technology in the traditional context of urban areas, connecting ubiquitous sensing technologies, computational power, and data about the urban environment to promote quality of life for people living in a particular community. To this aim, the focus of this study is on interpreting a linkage between society stated preferences and quantitative measures of livability by extracting information from survey-based methods and translating it to a quantitative framework using combined service industry and urban computing methodologies. This work focuses on four transportation planning-related research questions in this blended framework: understanding existing livability patterns, predicting heterogeneous perceptions of quality of life, prioritizing public preferences, and developing a multidimensional livability index (MLI).

Publication Title

International Conference on Transportation and Development 2018: Planning, Sustainability, and Infrastructure Systems - Selected Papers from the International Conference on Transportation and Development 2018

Share

COinS