College
Buchtel College of Arts and Sciences
Date of Last Revision
2024-06-04 07:34:44
Major
Psychology
Honors Course
3750:498
Number of Credits
3
Degree Name
Bachelor of Science
Date of Expected Graduation
Spring 2024
Abstract
Companies, industries, and places of business use artificial intelligence and statistics to predict the characteristics of their employees and staff. Data collected from these individuals is also used to make decisions about them regarding their work life, such as promotions, salaries, or within the hiring process. Two models that are commonly used throughout the field of psychology and specifically in industrial/organizational psychology are the linear regression and the logistic regression. Examining different classification models using Python shows the potential that there may be different models that are more accurate in their predictions of employee success, including a Random Forest model and a LightGBM model, which is short for gradient boosting model. The comparison of these models provides evidence suggesting that the Random Forest model and the LightGBM model predict employee productivity more accurately than a traditional linear regression model or a logistic regression model.
Research Sponsor
James Diefendorff
First Reader
Meghan Thornton-Lugo
Second Reader
Andrea Snell
Honors Faculty Advisor
Charles Waehler
Proprietary and/or Confidential Information
No
Recommended Citation
Ceylan, Beyza, "Classification Models Using Python In Industrial/Organizational Psychology" (2024). Williams Honors College, Honors Research Projects. 1864.
https://ideaexchange.uakron.edu/honors_research_projects/1864
Signatures
Comments
Examining how classification models using Python in industrial/organizational psychology could be more accurate than a linear or logistic regression model in predicting employee productivity and success in the hiring process.
Consultant In This Project: Nedim Ceylan