Abstract— The use of credit cards is increasing in today's
digital era. This increase has resulted in many cases of fraud
which have had a negative impact on credit card owners. To
overcome this, many financial institutions have developed credit
card fraud detection systems that can identify suspicious
transactions. This study uses a classification method, namely
random forest and decision tree to identify illegal transactions
using a credit card, which then compares the results and attempts
to create a model that can be useful for detecting fraud using a
credit card that is more accurate and effective. The result of this
study is that the accuracy provided by the Decision Tree Classifier
is 0.98, while the accuracy provided by the Random Forest
Classification is also 0.975. The conclusion obtained that the
decision tree has a higher level of accuracy compared to the
Random Forest Classification Algorithm, which is 98%. On the
other hand, the Random Forest classification algorithm has a
slightly lower level of accuracy compared to the Decision Tree
classification algorithm, with an accuracy rate of 97.5%