Comparison of different supervised learning models performance using flood dataset

In order to reduce the damage and fatalities caused by floods. Flood prediction is a critical task which helps to minimize damage and loss of life. This study evaluates the performance of various supervised learning models such as--K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression, and Naive Bayes--for flood prediction. In this paper work utilizes historical flood data to train and test these algorithms. Metrics such as precision, accuracy, recall, and F1-score are utilized to compare and test the efficiency, reliability of each model. By completing this experiment, we can find out which of the models is more efficient for flood prediction and helps in finding a reliable selection of suitable machine learning techniques for real-world flood forecasting applications. Which greatly contributes to the accurate predictions of floods and helps in reduces the loss of property and life.