This study examines the application of the Synthetic Minority Oversampling Technique (SMOTE) to addressclass imbalance within a dataset used for predicting high school major selection. The dataset comprises 468 traininginstances, including 306 labeled as 'IPA' and 162 labeled as 'IPS'. Despite the implementation of SMOTE, the results revealno significant enhancement in the predictive performance of the models, as both the SMOTE and non-SMOTE modelsachieved an accuracy of 100%, an F1-score of 100%, and a recall of 100%. This finding suggests that other factors, suchas the selection of relevant features, hyperparameter tuning, and model complexity, may have a more substantial impact onprediction performance. Additionally, the study proposes several recommendations for future research, includingconducting a more in-depth feature analysis, exploring alternative classification algorithms with advanced class imbalancehandling mechanisms, and performing meticulous hyperparameter optimization to improve overall model performance.