Document Type

Technical Report

Publication Date



Decision making -- Statistical methods, Transportation -- Planning -- Oregon -- Portland, Data mining


Urban transportation professionals are under increasing pressure to perform data-driven decision making and to provide data-driven performance metrics. This pressure comes from sources including the federal government and is driven, in part, by the increased volume and variety of transportation data available. This sudden increase of data is partially a result of improved technology for sensors and mobile devices as well as reduced device and storage costs. However, using this proliferation of data for decisions and performance metrics is proving to be difficult. In this paper, we describe a proposed structure for a system to support data-driven decision making. A primary goal of this system is improving the use of human time, effort and attention with side benefits of improved consistency and documentation.


This paper is a use case in support of Portland Observatory, a new research project, intended to explore how one might architect and build an observatory that understands and adapts to the wide variety of data gathered or otherwise available in a single domain. The project uses the city of Portland, Oregon, as a laboratory and example within which to explore these concepts.

Paper subsequently presented at BDUIC 2014, the Big Data and Urban Informatics Workshop, UIC, Chicago, IL, August 11-12, 2014.

Persistent Identifier