Abstract
House fires pose a threat to life and property in every society, such that laws, organisations and work systems have been established to protect communities. Motivated by statistics published annually by the Australian Productivity Commission (2021) showing little variation in lives lost, injuries or costs associated with house fires, this research demonstrates that large repositories of publicly available information about house fire incidents can be used to create predictive decision tools that could lower the impact of house fires on society. Interpreted through an activity theory lens, this research demonstrates how data mining can identify common features in public datasets and be used to create predictive models to identify future instances of house fires. The research proposes that this information be used by government, firefighting organisations, insurers, not for profits and the public to better prepare when house fires are more likely to occur.
Recommended Citation
Edwards, Andrew; Smith, Stephen; Busch, Peter; and Winchester, Donald, "Predictive Technologies for Strategic House Fire Management" (2022). ACIS 2022 Proceedings. 10.
https://aisel.aisnet.org/acis2022/10