Date of Award


Document Type


Degree Name

Master of Science in Computer Science


School of Computer Science and Engineering

First Reader/Committee Chair

Qiao, Haiyan


The US Census Bureau offers a wide range of data, and within this array, the American Community Survey 5-Year Estimate (ACS5) serves as a valuable resource for understanding the US population. This project embarks on an exploration of Machine Learning and the Software Development process with the goal of generating effective population projections from ACS5 data. The project aims to provide methods to make predictions for every city and town in the US, encompassing their total population and population divided into 5-year age groups. It's worth noting that while the generation of these projections is grounded in the generalized statistical likelihood computed by the machine learning models, there remains an expected margin of error for each prediction.

To effectively convey this margin of error alongside the series of predictions, the project leverages a technique known as conformal prediction, which delivers the error range in the form of conformalized quantile regression. The modeling process encompasses a variety of approaches, including both Statistical Machine Learning Models and Deep Learning Models. The ultimate results take the form of visualizations, comprising combined plots featuring selected statistics for specific cities and towns within the County of Riverside, serving as the test dataset. These final machine learning models successfully yield persuasive population growth projection curves.