Perbandingan Metode Smote Random Forest Dan Smote Xgboost Untuk Klasifikasi Tingkat Penyakit Hepatitis C Pada Imbalance Class Data

Abstract

Hepatitis causes around 1.4 million people die every year. This number makes hepatitis to be the largest contagious disease in the number of deaths after tuberculosis. Liver biopsy is still the best method for diagnosing the stage of hepatitis C, but this method is an invasive, painful, expensive, and can cause complications. Non-invasively method needs to be developed, one of non-invasif method is machine learning. Random Forest and XGboost are classification methods that are often used, since they have many advantages over classical classification methods. The SMOTE algorithm can be used to improve the accuracy of predictions from imbalanced data. the data in this study have 24 independent variables in the form of patients self-data, hepatitis C symptoms, and laboratory test results. The dependent variable in this study is a binary category, namely the level of hepatitis C disease (fibrosis and cirrhosis). The results showed that the random forest and XGboost had an accuracy of around 74% but the recall value was less than 2%. SMOTE random forest dan SMOTE XGboost have an accuracy & recall value more than 75%. SMOTE random forest has a higher accuracy for predicting fibrosis class while SMOTE XGboost is better in cirrhosis class. Variables that are more influental in determining hepatitis C stage are variables from laboratory test. Keyword : Fibrosis, Cirrhosis, Random Forest, SMOTE, XGboost

Performance Comparison of Grid Search and Random Search Methods for Hyperparameter Tuning in Extreme Gradient Boosting Algorithm to Predict Chronic Kidney Failure

“…One of the oversampling methods that can be used is the Synthetic Minority Oversampling Technique (SMOTE). The SMOTE method adds the amount of data from the minor class using the neighbor approach to make it equal to the major class [17]. In the case of credit scoring classification, the SMOTE method results in an accuracy value of 81.69%, which is relatively high; this value is better than other methods [18].…”

“…Cross-validation is a computer-intensive technique used to evaluate the performance of an algorithm model and the prediction error using all available examples as training and testing examples [17,28,29]. K-Fold Cross Validation was the method used in this study.…”

“…as the test data [30], which then the model results are the average results based on the training process [17].…”

Prediksi Harga Mobil Bekas dengan Machine Learning

“…Untuk meningkatkan akurasi pada random forest dengan melakukan hyperparameter diantaranya n_estimators dan max_depth. Parameter n_estimators ini yang akan menetukan berapa decission tree yang akan dibuat, sedangkan max_depth menyatakan seberapa dalam layer setiap decission tree akan dibuat (Syukron, Santoso, & Widiharih, 2020;Zhang, Yang, & Zhou, 2018). Tabel 7 adalah ringkasan pengaturan hyperparameter RF.…”

Implementation of Ensemble Techniques for Diarrhea Cases Classification of Under-Five Children in Indonesia

“…In [6], concluded that a hybrid method can increase AUC gradually with an increase in the percentage of oversampling. Related research was also conducted [15] by comparing SMOTE Random Forest and SMOTE XGBoost models on the HCV dataset. The results obtained that models with SMOTE can significantly increase the recall value from under 2% to more than 70%.…”