The thyroid is a vital gland in the human neck, regulating metabolism through its hormones. Hormonal disorders in the thyroid can significantly affect health. Data mining techniques, such as the random forest algorithm, are used to analyze thyroid disease data. Previous research has used methods such as Decision Tree and Support Vector Machine with high accuracy results. This study aims to apply the random forest method in the classification of thyroid disease diagnoses. Research questions include factors that affect accuracy, the effect of parameter changes on the model, and optimal data sharing. The results show that parameters such as the number of decision trees, maximum depth, and minimum number of samples can affect the accuracy of the model. The evaluation showed that the highest accuracy was obtained in the first test with a data split of 80/20 with an accuracy result of 99%. This study concludes that the random forest method is effective in improving the accuracy of thyroid disease diagnosis and the importance of parameter adjustment for optimal results.