Analysis of Naïve Bayes and K-Nearest Neighbors Algorithms for Classifying Fishermen Aid Eligibility

Abstract

This article analyzes the use of data mining with Naïve Bayes and K-Nearest Neighbor (KNN) algorithms to build classification models and evaluate their performance in identifying fishermen eligible for aid. The study aims to compare the effectiveness of these algorithms in handling imbalanced datasets using the Synthetic Minority Over-sampling Technique (SMOTE). The research applies SMOTE to improve the balance of the dataset before classification. Without SMOTE, Naïve Bayes achieved an accuracy of 97.01%, precision of 94.16%, recall of 96.67%, and F1-score of 95.39%. KNN, on the other hand, reached an accuracy of 94.04%, precision of 94.53%, recall of 86.00%, and F1-score of 90.06%. After applying SMOTE, both algorithms improved: Naïve Bayes attained an accuracy of 98.33%, precision of 96.86%, recall of 100.00%, and F1-score of 98.49%, while KNN reached an accuracy of 96.90%, precision of 97.72%, recall of 96.19%, and F1-score of 96.94%. The results show that Naïve Bayes, with SMOTE, outperforms KNN in managing data imbalance and accurately classifying eligible fishermen for aid.