Search

The literature provides multiple measures of diversity along a single demographic dimension, but when it comes to studying the interaction of multiple diversity types (e.g. age, gender, and race), the field of useable measures diminishes. We present the use of decision trees as a machine learning technique to automatically identify the interactions across diversity types to predict different levels of a dependent variable. In order to demonstrate the power of decision trees, we use five types of surface-level diversity (age, gender, education level, religion, and region of origin) measured via the standardized Blau index as independent variables and knowledge sharing as the dependent variable. The results of our decision tree approach relative to linear regression show that decision trees serve as a powerful tool to identify key demographic faultlines without "a priori" specification of a model structure.

• Existing C&DW facility location strategies focus on either GIS or optimization. • We propose a decision support tool that combines both GIS and optimization. • The tool allows for the evaluation of abandoned quarries as part of a C&DW strategy. • We demonstrate the efficacy of this combined tool on a case in the developing world. Increased stress on raw material and limited landfill space due to increasing rates of urbanization have encouraged efforts to divert Construction and Demolition Waste (C&DW) away from landfills toward sorting, recycling, and reusing. While these efforts have been successful in some countries (e.g., Germany, Netherlands), developing countries tend to suffer from illegal and haphazard dumping of C&DW. This study presents an optimization based decision support tool to select a cost and environmentally effective set of abandoned quarries to serve as C&DW landfills and processing facilities. The tool is composed of a GIS model and a mixed integer linear program that accounts for the complete waste management chain. A case study in Lebanon served as a testbed for the tool: A multi-criteria analysis was first used in GIS to evaluate the environmental suitability of candidate quarries based on five thematic groups: socio-economic, topography, geology, hydrology and infrastructure. The most suitable quarries were then inputted to the optimization model. Two out of 148 abandoned quarries in Mount Lebanon were deemed suitable for rehabilitation under the objectives set yielding a profit of 125 million US dollars over a 20 year span. Future challenges include enhancing the model by incorporating time and accounting for more recycling technologies. [ABSTRACT FROM AUTHOR]