Abstract Computer networks connected to the Internet can access information from all over the world very easily. However, the connection between the network and the Internet increases the potential for system failure. One of the methods that can be used in machine learning is the random forest algorithm method. Random forest is one of the methods in machine learning that is used to solve clarification problems. Based on the problems, it is necessary to classify malware where data is taken from malware datasets to make it easier to learn and distinguish the types of malware. The process consists of collecting datasets, pre-processing, training machine learning, and testing model performance. This study aims to find out the performance of Machine Learning using a random forest algorithm for malware- random forest classification. In this process, pre-processing of data is done by installing several Python libraries. Pandas is an open-source Python library that is usually used for data analysis needs. The model is trained on a dataset with various features and the results show a high accuracy of 99%. The random forest model provides excellent results without preprocessing the data. The results are good even if the data is not balanced. There is no need to use any technique to balance it. Scaling is not necessary. The random forest model is a recursive partitioning model that depends on data partitioning as it works on splitting the feature values and does not perform any calculations in it. The results indicate that the model has a precision of 0.99.