Salary Prediction with Analyzing Affected Elements by using Pearson Correlation

Abstract

This paper proposes a model for predicting salaries based on the 1994 Census Database to predict whether the final salary is over 50 thousand dollars or not. In order to do this, the researchers will identify various factors that may influence wages and analyze their impact on salary. To find the most accurate model, the researchers will use 32561 records, each containing 15 elements, and apply three different machine learning algorithms: Random Forest, Decision Trees, and Logistic Regression. These algorithms will be evaluated using a 5-fold cross validation method, which is a commonly used technique for measuring the performance of machine learning models. The goal of this study is to provide guidance on wage levels for individuals entering the workforce, as well as to understand how various factors may affect an individual's salary. This information could be useful for job seekers, as well as for employers looking to attract top talent. By identifying the factors that influence wages, the model could also potentially help policy makers and other stakeholders to address issues of wage inequality and fairness in the workforce. Overall, the model developed in this study has the potential to provide valuable insights and guidance for a wide range of individuals and organizations.