Search results

The purpose of this paper is to provide a review of literature about recruitment, retention and resignation among non-career firefighters.

A systematic review was conducted to identify factors associated with the recruitment, retention and resignation of non-career firefighters. The authors divided the results into three topics and four levels for further analysis.

27 articles are included in the review. Most research addresses retention at an organizational level and indicates a link between job satisfaction and factors such as supervisor support, recognition and close relationships within the workgroup. Further, a recurring reason that contributes to resignations seems to be family related (e.g. partner disapproval).

There is a lack of European and Asian research into non-career firefighters. The included research papers generally have low response rates and the sample is often mostly male and Caucasians from a limited area.

The identified factors offer deeper understanding and can help practitioners in their pursuit of the sustainable retention of non-career firefighters.

Because securing adequate numbers of non-career firefighters is important, there is a need to synthesize current evidence to identify and further understand which factors contribute to retention. To the authors' knowledge, this is the first systematic review to synthesize such evidence about non-career firefighters.

This study aims to develop a machine learning model to detect structure fire fatalities using a dataset comprising 11,341 cases from 2011 to 2019.

Exploratory data analysis (EDA) was conducted prior to modelling, in which ten machine learning models were experimented with.

The main fatal structure fire risk factors were fires originating from bedrooms, living areas and the cooking/dining areas. The highest fatality rate (20.69%) was reported for fires ignited due to bedding (23.43%), despite a low fire incident rate (3.50%). Using 21 structure fire features, Random Forest (RF) yielded the best detection performance with 86% accuracy, followed by Decision Tree (DT) with bagging (accuracy = 84.7%).

Limitations of the study are pertaining to data quality and grouping of categories in the data pre-processing stage, which could affect the performance of the models.

The study is the first of its kind to manipulate risk factors to detect fatal structure classification, particularly focussing on structure fire fatalities. Most of the previous studies examined the importance of fire risk factors and their relationship to the fire risk level.