Pulsars are neutron stars which offer a wealth of information for astronomers. The objective of this experiment is to compare four pulsar classification algorithms: two ANNs, a Very Fast Decision Tree, and an ensemble algorithm. The data set, HTRU2 contains 17,898 instances of pulsar candidates with eight input attributes and one target attribute for each instance. The data will be preprocessed and divided into three training sets: an unscaled, scaled, and proportionate (50% pulsars) sets. Each training set will be used on each classification algorithm. The results of this experiment concluded that the Very Fast Decision Tree using the Proportionate Training Set was the best model with a recall of 98.09% and FPR of 0.32% at its most efficient.