Comparison of Decision Tree with Linear Discriminant Analysis to Accurately Predict Pulsar Stars To Explore Space Efficiently

An analysis was conducted on existing methodology and approaches for predicting pulsars, which included the use of observation-based filtering techniques. We examine the decision tree approach and the linear discriminant analysis methodology in relation to improving the accuracy of Pulsar Star Predictions for the Progress of Space Exploration. Our evaluation criteria include a 95% confidence interval, a 0.8 G power, and 300 sample sets, with 10 repeats each set. With 12,509 rows and 9 columns, the identification dataset included 7,000 tuples of training set data, derived from the Kaggle dataset. In comparison to the decision tree algorithm's 96.53% accuracy, the Linear Discriminant Analysis approach achieves a much higher 93.53% (p=0.261, p<0.05). Planets in this system should circle a broad array of stars, with rocky cores and masses equal to Earth. Decision trees greatly enhance accuracy when compared with Linear Discriminant Analysis.