Bridging the SME reporting gap: A new model for predicting Scope 1 and 2 emissions

Area of Science:

• Environmental Science
• Data Science
• Business Analytics

Background:

• Small and medium-sized enterprises (SMEs) are crucial to the economy but often excluded from formal emissions reporting.
• Existing emissions estimation methods for SMEs are either too general (sectoral averages) or too resource-intensive (firm-level data).
• SMEs are frequently under-engaged in sustainability initiatives due to data and resource constraints.

Purpose of the Study:

• To develop and validate a novel statistical model for predicting Scope 1 and Scope 2 greenhouse gas emissions for SMEs.
• To provide an accessible and scalable emissions estimation tool for a segment of businesses typically lacking formal reporting capabilities.
• To enhance the climate engagement of smaller businesses through simplified emissions data.

Main Methods:

• Trained a statistical model on financial transaction data from over 100,000 UK SMEs.
• Evaluated various predictors, including industry-level variables and basic emission intensity.
• Assessed model performance using R-squared (RSQ) values and out-of-sample testing, comparing against sector-level estimates.

Main Results:

• The model achieved high predictive accuracy with RSQ values of 0.89 for Scope 1 and 0.72 for Scope 2 emissions.
• Incorporating industry-level variables significantly improved predictive accuracy compared to basic emission intensity.
• The model demonstrated diminishing returns from increased complexity, supporting a parsimonious design and improving accuracy by up to 50% over sector-level estimates.

Conclusions:

• A novel, data-driven statistical model offers a simpler and more accurate method for SME emissions estimation.
• The model leverages accessible financial data, overcoming barriers to sustainability reporting for smaller businesses.
• This approach can support broader climate action and engagement among SMEs.