This research aims to improve the process of fi ndingalternative drugs by utilizing artifi cial intelligence algorithms. It isnot an easy task for human beings to classify the drugs manually,as this requires much longer time and more effort than doing itusing classifi ers. The study focuses on predicting high-qualitymedical drug data by considering ingredients, dosage forms,and strengths as features. Two datasets were generated fromthe original drug dataset, and four machine learning classifi erswere applied to these datasets: Random Forest, Support VectorMachine, Naive Bayes, and Decision Tree. The classifi cationperformance was evaluated under three different scenarios, whichvaried the ratio of the training and test data for both datasets,as follows: (i) 80% (training) and 20% (test dataset), (ii) 70%(training) and 30% (test dataset), and (iii) 50% (training) and50% (test dataset). The results indicated that the Decision Tree,Naive Bayes, and Random Forest classifi ers showed superiorperformance in terms of classifi cation accuracy, with over 90%accuracy achieved in all scenarios. The results also showed thatthere was no signifi cant difference between the results of thetwo datasets. The fi ndings of this study have implications forstreamlining the process of identifying alternative drugs.