This paper mitigates the effect of blackhole attacks in mobile ad hoc networks according to the traffic of the Ad-hoc Ondemand Distance Vector (AODV) routing protocol. The algorithm consists of two parts: In part one, machine learning algorithms are used to detect whether the network suffers from a blackhole attack or not. Part two will be activated if there is a blackhole attack. To block the compromised node, the proposed algorithm in stage two removes the highest sequence number in the route reply as the blackhole node increases the sequence number in the route reply. According to the simulation results, machine learning algorithms used in blackhole detection show an average accuracy of 97.8% for the Random Forest classifier. Throughput, delay, and packet delivery ratio (PDR) are enhanced in part two of the proposed approach.