<![CDATA[Abstrak: Stroke merupakan salah satu penyebab utama kematian dan kecacatan jangka panjang di dunia. Peningkatan kasus stroke mendorong pemanfaatan teknologi machine learning untuk membantu prediksi risiko penyakit secara cepat dan akurat. Penelitian sebelumnya telah menggunakan algoritma seperti Support Vector Machine dan Random Forest, namun sebagian besar masih berfokus pada performa model dan belum mengintegrasikan hasil prediksi dalam media visual yang interaktif. Penelitian ini bertujuan membangun model prediksi risiko stroke menggunakan algoritma Logistic Regression serta mengimplementasikannya dalam dashboard interaktif. Dataset yang digunakan berasal dari Kaggle dengan jumlah data sebanyak 5110. Tahapan penelitian meliputi preprocessing data, pembagian data latih 80% dan data uji 20%, serta pelatihan model menggunakan Logistic Regression. Hasil penelitian menunjukkan model memperoleh akurasi sebesar 92% dan ROC-AUC sebesar 84%. Dashboard interaktif yang dikembangkan mampu menampilkan probabilitas risiko stroke dan variabel yang berpengaruh sehingga membantu pengguna memahami hasil prediksi secara lebih efektif.Kata kunci: Data Mining; Logistic Regression; StrokeAbstract: Stroke is one of the leading causes of death and long-term disability worldwide. The rise in stroke cases has driven the use of machine learning technology to help predict disease risk quickly and accurately. Previous research has employed algorithms such as Support Vector Machines and Random Forests; however, most studies have focused primarily on model performance and have not integrated prediction results into interactive visual media. This study aims to build a stroke risk prediction model using the Logistic Regression algorithm and implement it in an interactive dashboard. The dataset used comes from Kaggle, containing 5,110 data points. The research stages include data preprocessing, splitting the data into an 80% training set and a 20% test set, and training the model using Logistic Regression. The results show that the model achieved an accuracy of 92% and an ROC-AUC of 84%. The developed interactive dashboard displays stroke risk probabilities and influencing variables, helping users understand the prediction results more effectively..Keywords: Data Mining, Logistic Regression, Stroke]]>
