This document summarizes a study that used machine learning techniques to predict income levels using the Adult Dataset from the UC Irvine Machine Learning Repository. The author applied weighted k-nearest neighbors and random forest models to the dataset, which contains both categorical and continuous variables. Simple visualizations and linear models on education levels, age, and hours worked per week showed correlations with higher income. The results section will compare error rates from the weighted k-nearest neighbors and random forest models for predicting income levels above or below $50k.