The growth of cities and the mobility of their inhabitants often generate traffic jams. In order to diminish this problem, cities began to implement Intelligent Transportation Systems (ITS), such as real-time control and monitoring of public transportation buses, smart traffic lights, mobile applications to inform passengers. ITS are a reliable source of data collection for further analysis. This research aims to perform a clustering analysis to detect traffic jams, for which the Parallel Social Spider Optimization (P-SSO) algorithm was used. The choice of the P-SSO algorithm was made based on the previous results where the P-SSO algorithm was compared with the K-means and Social Spider Optimization (SSO) algorithms to solve clustering problems. On the first stage of this research, the P-SSO algorithm was used to define traffic jam states. In the second stage, the P-SSO algorithm was used to detect traffic jam areas based on the geospatial data generated by public transport buses in Cusco-Perú. This clustering analysis was performed on the main streets of the city between June and August 2019. Further, an application was developed that allows to check graphically the clusters obtained.