Ingenious K Nearest Neighbor based Systematic prediction of Early Floods in Uncertain Weather Forecasts

The purpose of this research is to create and evaluate a clever K Nearest Neighbor-based systematic prediction system against the Decision Tree Classifier method for early flood detection in the face of erratic weather forecasts. The dataset was gathered from kaggle, a well-known website for group collaboration, datasets, and contests related to data science and machine learning. Employed with a sample mean size of 20 sets, and a decision tree classifier has been utilized to increase the accuracy of the current research. A total of 40 sets are being compared using K-Nearest Neighbor. The ClinCalc software appliance has been utilized to compute the average accuracy of the current study. The implementation was done in Python Programming Language and by using the SPSS Software, the statistical analysis is displayed. Following the completion of this study, the decision tree classifier and K-Nearest Neighbor both reached 98% and 95% accuracy, respectively. After performing an independent samples T-Test analysis, p=0.000 (p<0.05) was discovered to be the significance value, indicating statistical significance. The research adds to the machine learning algorithm emphasizing that the current study combines the decision tree classifier with the K-Nearest Neighbor algorithm. Following the completion of the research, this highlights the potential of the k nearest neighbor as a useful tool in this sector.