A machine learning model for Alzheimer's disease prediction is proposed in this study. The authors evaluated three algorithms—decision tree (DT), extreme gradient boosting (XGB), and random forest (RF)—for predicting Alzheimer's disease using the Open Access Series of Imaging Studies (OASIS) dataset available on Kaggle. The dataset was balanced using the synthetic minority oversampling technique (SMOTE) to address class imbalance. The proposed methodology, SMOTE-RF, combined SMOTE with RF to improve prediction accuracy. The results showed that SMOTE-RF achieved the highest accuracy of 95.03% on the balanced dataset. The study also compared the performance of the three algorithms on both imbalanced and balanced datasets, finding that RF performed best on the balanced dataset with 95.03% accuracy. The study highlights the importance of early diagnosis in Alzheimer's disease and the potential of machine learning in improving prediction accuracy. The authors also discuss the limitations of their approach, including its reliance on pre-existing datasets and the challenges of integrating the model into clinical practice. The study concludes that early diagnosis and intervention are crucial for improving patient outcomes and reducing the societal and financial burden of Alzheimer's disease.A machine learning model for Alzheimer's disease prediction is proposed in this study. The authors evaluated three algorithms—decision tree (DT), extreme gradient boosting (XGB), and random forest (RF)—for predicting Alzheimer's disease using the Open Access Series of Imaging Studies (OASIS) dataset available on Kaggle. The dataset was balanced using the synthetic minority oversampling technique (SMOTE) to address class imbalance. The proposed methodology, SMOTE-RF, combined SMOTE with RF to improve prediction accuracy. The results showed that SMOTE-RF achieved the highest accuracy of 95.03% on the balanced dataset. The study also compared the performance of the three algorithms on both imbalanced and balanced datasets, finding that RF performed best on the balanced dataset with 95.03% accuracy. The study highlights the importance of early diagnosis in Alzheimer's disease and the potential of machine learning in improving prediction accuracy. The authors also discuss the limitations of their approach, including its reliance on pre-existing datasets and the challenges of integrating the model into clinical practice. The study concludes that early diagnosis and intervention are crucial for improving patient outcomes and reducing the societal and financial burden of Alzheimer's disease.