SUMMARY
Hepatitis is an inflammatory liver disease generally caused by a virus that attacks and causes damage to the cells and function of the liver. Hepatitis is the precursor to liver cancer. One of the things that can be done to reduce the rate of Hepatitis C sufferers is early detection by utilizing information technology. The detection system uses artificial intelligence with classification techniques. The classification technique used is by using the AdaBoost and SLP algorithms via the percentage split method and K-fold Cross Validation. In percentage split, the split data size was chosen as 80% and for the test data it was 20% and for K-fold Cross Validation a k value of 10 was used. The results of applying these two methods showed that percentage split worked better than K-fold Cross Validation due to the increase in the percentage value of the precision, recall and accuracy values of each algorithm. For the performance results of each algorithm, AdaBoost obtained accuracy, precision and recall values in the percentage split method, namely 86%, 63.8% and 84.8%. Then for the K-fold Cross Validation method, the AdaBoost algorithm obtained accuracy, precision and recall values of 90%, 63.8% and 25.8%. Meanwhile, the SLP algorithm using the percentage split method obtained accuracy, precision and recall values, namely 98%, 84.8%, 84.8%. And to use the K-fold Cross Validation method in the SLP algorithm, the accuracy, precision and recall values are 95%, 39.8% and 53.4%. From the results obtained, it can be concluded that the SLP algorithm is the best algorithm for solving Hepatitis C disease classification.