Data-Driven Sustainability: A Machine Learning Approach to Assessing ESG Performance in B Corporations
Description
The purpose of this research is to create predictive models for a leading sustainability certification - the B Corporation certification issued by the non-profit company B Lab based on the B Impact Assessment. This certification is one of many that are currently being used to assess sustainability in the corporate world, and this research seeks to understand the relationships between a corporation's characteristics (e.g. market, size, country) and the B Certification. The data used for the analysis comes from a B Lab upload to data.world, providing descriptive information on each company, current certification status, and B Impact Assessment scores. Further data engineering was used to include attributes on publicly traded status and years certified. Comparing Logistic Regression and Random Forest Classification machine learning methods, a predictive model was produced with 87.58% accuracy discerning between certified and de-certified B Corporations.
Date Created
The date the item was original created (prior to any relationship with the ASU Digital Repositories.)
2024-05
Agent
- Author (aut): Brandwick, Katelynn
- Thesis director: Samara, Marko
- Committee member: Tran, Samantha
- Contributor (ctb): Barrett, The Honors College
- Contributor (ctb): School of Mathematical and Statistical Sciences