The recent rise in fire incidents in Anambra State has resulted in displacement, stress, psychological, adverse effect on the lives of its inhabitants and a devastating consequence on the economy. The objectives of the study include examining the estimated value of properties loss due to fire outbreak within the study period and to employ the Random Forest regression model to predict the estimated losses associated with fire disasters in Anambra State. The data for the study was a secondary data obtained from the records Department of the Anambra State Fire Service, Headquarters Awka. The study used the Random Forest regression method to analyze the data obtained in this study. The Random Forest regression analysis was employed to predict the estimated value of properties loss (EVPL) due to fire outbreak. The explanatory variables used for the prediction of the response variable were Number of victims (NV), Percentage of Plain Land (PL), Population Size (PS), Population Density (PD) and Actual Revenue by LGA (ARLGA). The findings of the study revealed that EVPL has a higher Skewness and Kurtosis followed by NV and the least was found to be PL. Further result revealed that the percentage of variance explained was 12.03%, sum of square error (SSE) was 31.41, root mean square error (RMSE) was 0.7236 while the R-square was 59.18%. This result implies that the model was moderately positively adequate since it recorded a positive coefficient of determination. The findings from the variable importance analysis showed that Population Density played a major role in the estimation of the response variable followed by the number of victims while population size was found to be the least important variable for estimating the response variable.
Nyagawa, Z. M. “An investigation of the immediate causes of fire disasters in boarding secondary schoolshttp://oapub.org/edu/index.php/ejes/article/view/1
Setiawan, C., Handawati, R., and Ermalia “Analysis of Influence Settlement Densityon the Fire Hazards
settlement at Cengkareng Subdistrict”, West Jakarta, IOP Conf. Series: Earth and Environmental Science, 2020, 412(012011): 1-9. doi:10.1088/1755-1315/412/1/012011https://iopscience.iop.org/article/10.1088/1755-1315/412/1/012011/meta
Odaudu, U. S. “Analysis of the Overview of the Causes of Fire Outbreaks in Nigerian Markets”, CARD
International Journal of Environmental Studies and Safety Research (IJESSR), 2017, 2(2): 1-9.https://www.afrigistjournals.com/index.php/ajlaem/article/view/v1i1a1
Breiman, L. “Manual on setting up, using and understanding random forests”, V3.1 2002. https://oz.berkeley.edu/users/breiman/Using_random_forests_V3.1https://proceedings.neurips.cc/paper/2013/hash/e3796ae838835da0b6f6ea37bcf8bcb7-Abstract.html
Cutler, A., Cutler, D.R. and Stevens, J.R. “Random forests”, Chapter in Machine Learning, 2011.
DOI:10.1007/978– 1 – 4419 – 9326 – 7 _ 5. Source: DBLP"https://link.springer.com/protocol/10.1007/978-1-60761-744-0_17
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.