Salary Prediction Classification

The aim of this paper is to statistically analyze salary classification by observing people's work class, education, race, gender, and other characteristics and categorizing salary prediction based on these characteristics. To get at the results, techniques like data visualization, statistical analysis and machine learning techniques were applied. The regressions, support vector machine, artificial neural network, random forest, and Xgboost machine learning algorithms are used to classify salary classification. Research questions are developed and analyzed prior to prediction in order to better understand relationships between variables in the data. Data cleaning techniques are used to create clean, appropriate data for the study. After the dataset has been cleaned, models and statistical tests are run. Sensitivity, accuracy and F1 score were used to assessed models due to the large number of the categorical variables. The analysis is conducted using R- studio.