Application of Data Mining Approach for Profiling Fire Incidents Reports of Bureau of Fire and Protection

摘要: The study aims to create a fire model that can generate pattern obtain profile of incidents in Manila help facilitate the assessment by providing quick, thorough, and scientific analysis data, outputs which turn be utilized as basis for formulation new programs prevention activities. researchers applied K-means clustering approach Elbow method using Python scikit-learn tool process dataset produce number clusters with centroid correlation heatmap resulted five clusters. most noticeable result is "Day" attribute, Wednesday Thursday, are similar across all In addition, occurred between 12:00 NN 4:00 PM, around lunchtime afternoon siesta. also shows poor vulnerable likewise, middle class. It concludes government reconsider its services on protection issues disaster management. Data mining techniques incident reports was limited Philippines. With this. more work should carried out prediction predicting presence so firefighter could immediately respond.