Comparing various Machine Learning Techniques for Predicting the Salary Status

EasyChair Preprint 2625

Abstract

Supervised Learning and Unsupervised Learning method is used for classification of the data for predicting that which machine learning technique will classify the data sets of salary status of the people that who are less than or equal to 50000 salary or greater than 50000 salary more efficiently. We take the attributes as age, job_type, ed_type(education type), capital gain, capital loss, race, work hours per week, native country, salary status , relationship ,occupation, marital status, gender. We use four classifier methods Naïve Bayes, Random Tree, Random Forest, REPTree for classifying the data sets. After classifications we apply K-means algorithm for clustering the data.

Keyphrases: K-means, Naïve Bayes, REPTree, Random Forest, Random Tree, supervised learning

@booklet{EasyChair:2625,
  author    = {Suyash Srivastava and Deepanshu Sharma and Priyanka Sharma},
  title     = {Comparing various Machine Learning Techniques for Predicting the Salary Status},
  howpublished = {EasyChair Preprint 2625},
  year      = {EasyChair, 2020}}