<![CDATA[Identification of students' interests and talents is one of the important aspects in the development of individual potential in the educational environment. However, this process often faces challenges in terms of accuracy and efficiency, especially when done manually. This research aims to develop a machine learning-based decision support system that is able to optimize the process of identifying students' interests and talents at the Senior High School level. The data used in this study include academic grades, interest and aptitude test results, and participation in extracurricular activities. Through the application of machine learning algorithms such as Decision Tree and Random Forest, this system is able to analyze patterns in the data and provide accurate recommendations related to the interests and talents that are most suitable for each student. The results of the trial show that the developed system has succeeded in increasing the accuracy of identifying students' interests and talents by up to 84%, compared to conventional methods. This system is expected to be an effective tool for teachers and counselors in designing educational programs that are more personalized and in accordance with the potential of each student.ABSTRAKIdentifikasi minat dan bakat siswa merupakan salah satu aspek penting dalam pengembangan potensi individu di lingkungan pendidikan. Namun, proses ini sering kali menghadapi tantangan dalam hal akurasi dan efisiensi, terutama ketika dilakukan secara manual. Penelitian ini bertujuan untuk mengembangkan sistem pendukung keputusan berbasis machine learning yang mampu mengoptimalkan proses identifikasi minat dan bakat siswa di tingkat Sekolah Menengah Atas (SMA). Data yang digunakan dalam penelitian ini mencakup nilai akademik, hasil tes minat dan bakat, serta keikutsertaan dalam kegiatan ekstrakurikuler. Melalui penerapan algoritma machine learning seperti Decision Tree dan Random Forest, sistem ini mampu menganalisis pola-pola dalam data dan memberikan rekomendasi yang akurat terkait minat dan bakat yang paling sesuai untuk setiap siswa. Hasil uji coba menunjukkan bahwa sistem yang dikembangkan berhasil meningkatkan akurasi identifikasi minat dan bakat siswa hingga 84%, dibandingkan dengan metode konvensional. Sistem ini diharapkan dapat menjadi alat yang efektif bagi guru dan konselor dalam merancang program pendidikan yang lebih personal dan sesuai dengan potensi setiap siswa.]]>
