A web application for measuring performance of fire stations through machine learning techniques

The rapid development of information systems enables the efficient use of data in decision-making process of organizations. The processing and analysis of raw data and including them in decision-making processes have a great importance for more effective management, performance measurement and effective use of public fundings in public institutions and organizations. Within the scope of this study, a system was designed to support the decision-making processes of the Izmir Fire Department directly. The study was carried out by constantly exchanging ideas with the authorized persons of the Fire Department and taking into consideration the needs of the fire brigade. A web-based application, which aims to support the decision-maker in the decision-making process and to obtain useful information from the existing data by making instant and future inferences, was developed. During the development process of the application, the Fire Report forms, which were created, kept on paper and stored in archives by Izmir Fire Department, were digitized. The current situation and performance of the fire brigade has been revealed by making various queries and analyzes from the forms which are saved to database by digitizing them. In addition, by making forecasts for the future, the application has been turned into a system that provides forward-looking information and shows the current situation and performance. Time series analysis and machine learning techniques were used to make predictions for the future. Queries, analyzes and predictions in this web application were reported to the decision maker with graphs, numerical values and maps. Keeping fire reports forms into databases instead of archives has an important role to prevent risks such as absence of data, having deformed data, and non-particpation of data into decision making process effectively. The application will provide support for decision-making on issues such as stock management, human resource management, fire station location selection, by converting raw data into useful information.