With the increasing use of network and computer resources on the Internet, defending against attacks and intruders has become a key concern. One way to assess the network security problem is to detect intrusions. An intrusion detection system (IDS) gives your infrastructure an additional layer of security. As cybercrime has evolved over time, intrusion detection technology has also advanced significantly. Researchers have worked to enhance intrusion detection while maintaining network performance ever since the technology's development in the middle of the 1980s. An Intrusion Detection System (IDS) was implemented using the extensive dataset available from the Canadian Institute of Cybersecurity (CIC). This paper proposes a network intrusion detection algorithm based on the random forest classifier. The dataset was appropriately formatted and some records containing non-numeric values were weeded out. The record set was processed using the SCIKIT library in Python which offers Random Forest Classifier (RFC) object for machine learning. After the RFC was trained with 70% of the records, the testing carried out using the remaining 30% of records indicated result accuracy of 99.853%.