Developing Predictive Risk Analytic Processes in a Rescue Department

Abstract

Aging and home care bias in elder care has changed the supply chain environment of rescue departments. The current situation requires data-driven approaches to manage risk and resiliency in such a way that decision-makers can take reactive, proactive, and prescriptive actions. In practice, public service providers should anticipate risks and prevent accidents that arise from the various needs of residents in home environments. The new risk prevention policies should be built on cooperation between the rescue board and the social and healthcare sectors in order to consolidate and process large amounts of data and to develop a foundation for anticipating and managing safety risks in housing. This chapter explores the data structure requirements needed to use the predictive analytics that consolidates information from the logs of the rescue service and social and healthcare agencies as well as the electricity consumption data of residents. In addition, demographic descriptors of the regions should be connected to the process logs. The data sources form a diverse body of data that can be significantly leveraged in three areas of risk management to (1) estimate operation response, (2) create a risk profile of individuals, and (3) understand the chain of events that lead to accidents.