College

College of Engineering and Polymer Science

Date of Last Revision

2026-04-28 12:31:09

Major

Computer Science

Honors Course

CPSC-498 002

Number of Credits

2

Degree Name

Bachelor of Science in Computer Science

Date of Expected Graduation

Spring 2026

Abstract

Macroeconomic predictions present challenges in machine learning due to the rarity of economic recessions, the constantly-changing matter of global markets, and severe class imbalance in historical data. This project focuses on predicting the onset of United States economic recessions within a 12-month window using Python and Jupyter Notebook. A machine learning pipeline was developed utilizing multiple models: Logistic Regression, Random Forest, XGBoost, and Long Short-Term Memory (LSTM) neural networks. For class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied strictly to training data, paired with Platt scaling for calibration on thresholds. The resulting models were evaluated in the 2005 to 2015 period, specifically testing the ability to predict the 2008 Great Financial Crisis using pre-2005 data. Furthermore, a soft-voting ensemble method was used to attempt a better prediction.

Research Sponsor

Dr. Zhong-Hui Duan

First Reader

Dr. Yingcai Xiao

Second Reader

Dr. John C. Hoag

Honors Faculty Advisor

Dr. Zhong-Hui Duan

Proprietary and/or Confidential Information

No

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.