Asteroid detection is a common field in astronomy for planetary defense, requiring observations from survey telescopes to detect and classify different objects. The amount of data collected each night is continually increasing as new and better-designed telescopes begin collecting information each year. This amount of data is quickly becoming unmanageable, and researchers are looking for ways to better process this data. The most feasible current solution is to implement computer algorithms to automatically detect these sources and then use machine learning to create a more efficient and accurate method of classification. Implementation of such methods has previously focused on larger asteroids, but this leads to less accuracy in classifying smaller and slower-moving asteroids. We use the source data from the Near-Earth Object Widefield Infrared Survey Explorer (NEOWISE) survey telescope to create a preprocessing pipeline allowing for better training and testing data for machine learning algorithms. We were able to create a pipeline that finds sources on an image within 0.02 degrees as well as a collection of data on the known sources. Next, we used several machine learning classifying models, including a logistic regression classifier, a support vector machine (SVM), a naïve Bayes classifier, and a random forest. Finally, we present and discuss these results as a confusion matrix for each model, describing the ability to classify a source as an asteroid or not. This was done with only the numerical data collected. In the future, to create a better classifier, we would use this data along with classified images to develop a system that could predict the possibility of a detected source within a NEOWISE image being an asteroid or not.