Artificial Intelligence in Socioeconomic Research: Identifying Key Drivers of Unemployment Inequality in the U.S

Abstract

Unemployment inequality remains one of the most vexing socioeconomic quagmires confronting the United States. This research project aimed to pinpoint how AI can be applied in the enumeration of key drivers of unemployment inequality in the United States and set a framework for further research and policy development. In this study, the researcher has drawn a massive volume dataset from the Economic Policy Institute's State of Working America Data Library, along with research performed by the Federal Reserve Bank of St. Louis. The unemployment incidents data was classified in terms of age, education level, gender, race, and other demographic factors. Subsequently, the analyst employed Linear Regression from the Scikit-learn library. Overall performance evaluation showcased that linear regression performed excellently with the least error in MSE and RMSE and, hence, was the best in terms of accurately predicting unemployment indicators. Accurate prediction of the unemployment rate using the proposed linear regression model can help the U.S. government proactively warn against economic downturns by deploying the. Besides, by executing the Linear Regression, government officials can influence favorable policies through tax incentives or labor laws. Evidently, the linear regression framework is a powerful AI tool that can help bring huge enhancements to unemployment inequality research and policy development in the future. This model not only provides a quantification of the relationships but allows for the making of predictions, thus making it useful for evaluating the possible results of different policy scenarios. Furthermore, the Linear Regression framework can also be used in the assessment of the effectiveness of pre-existing policies aimed at reducing unemployment.