Comparison of the Performance Results of C4.5 and Random Forest Algorithm in Data Mining to Predict Childbirth Process

Abstract

Technology advancements in the world of information have made it easier for many people to process data. Data mining is a process of mining more valuable information from large data sets. The research aims to determine the difference between the C.45 and random forest algorithms in data mining to predict the childbirth process of pregnant women. It compares the accuracy of the performance results of the C4.5 and random forest algorithms to predict the delivery process for pregnant women. Then, experimental research is conducted to classify the childbirth process in Situbondo, Indonesia, by applying the C.45 and the random forest algorithm in the data mining. The decision tree J48 algorithm is used for the C4.5 algorithm in the research. Both algorithms are compared for their error classification and accuracy level. The research uses 1,000 data for training and 200 data for testing. The results show the accuracy of implementing the C4.5 and random forest algorithms with data mining using 10-fold cross-validation, generating 96% and 95% as correctly classified data. Then, the Relative Absolute Error for both algorithms has the same result. It is 15%. The C4.5 algorithm has a better result than the random forest algorithm by comparing the performance results. Further research can add more data to improve the accuracy of the analysis results by using another algorithm.

Decision Tree based Data Modelling for First Detection of Thalassemia Major

“…Then, C4.5 is a modification of ID3 by expanding the scope of ID3 which only supports categorical data to support continuous data and missing values [9]. Basically, C4.5 works the same way as ID3.…”

“…The Confusion Matrix has evaluation components such as True Positive (TP), True Negative (TN), False Positive (FP) and False Negative (FN). The similarities of the Accuracy, Precision, Recall, and F1-Score metrics can be seen in Equations ( 7), ( 8), (9), and (10), respectively.…”

“…Something similar was also done by [7] and [8] in applying ID3 to classify typhoid fever and stroke in the medical world. C4.5 is a modification of ID3 that utilizes information entropy [9]. [10] use C4.5 to predict the procurement of office machine equipment so that it is effective according to conditions and needs.…”