This webinar explores the quality of Scope 3 emissions data in terms of divergence and composition, and the performance of machine-learning models in predicting Scope 3 emissions. We do so using the Scope 3 emission datasets of three of the largest data providers (Bloomberg, Refinitiv Eikon, and ISS). We find considerable divergence between third-party providers, making it difficult for investors to know their ‘real’ exposure to Scope 3 emissions. Surprisingly, divergence exists between the datasets for emissions values that have been reported by firms (68% identical data points between Bloomberg and Refinitiv Eikon). The divergence is even larger for ISS when it adjusts reported values using its proprietary models (0% identical data points). With respect to the composition of Scope 3 emissions, firms generally report incomplete compositions, yet they are reporting more categories over time. There is a persistent contrast between relevance and completeness in the composition of Scope 3 emissions across sectors, as irrelevant categories such as travel emissions are reported more frequently than relevant ones, such as the use of products and processing of sold products. We also find that the application of machine learning algorithms can improve the prediction accuracy of the aggregated Scope 3 emissions (up to 6%) and its components, especially when each category is estimated individually and aggregated into the total Scope 3 emissions values (up to 25%). It is easier to predict upstream emissions than downstream emissions. Prediction performance is primarily limited by low observations in particular categories, and predictor importance varies by category. We conclude that users of the Scope 3 emission datasets should consider data source, quality and prediction errors when using data from third-party providers in their risk analyses. Keywords: Scope 3 emissions; Carbon footprint; Climate finance; Machine learning; transition risk; Errors-in-variables

Speakers: Associate Prof. Ivan Diaz-Rainey; Dr. Quyen Nguyen

Ivan Diaz-Rainey is the Director, Climate and Energy Finance Group (CEFGroup) at the University of Otago, New Zealand. He is Associate Editor of the Journal of Financial Regulation and Compliance and Journal of Sustainable Finance & Investment, and has previously held academic positions at the University of East Anglia (Norwich, UK), the European University Institute (Florence, Italy), where he was a Jean Monnet Fellow, and the Higher Colleges of Technology (Abu Dhabi, UAE). He has conducted research, policy and consultancy work for a number of organisations, including the Ministry for the Environment (MfE), OECD, E.ON UK plc, the European Capital Markets Institute (ECMI) and the Asian Development Bank Institute (ADBI). His research expertise includes climate finance, carbon markets, energy finance, banking, financial regulation, and energy and environmental policy. He is Principal Investigator on a Marsden Fund project on climate-change risks to property values and the related implications for financial stability funded by Royal Society of New Zealand and undertaken in collaboration with GNS Science, Bodeker Scientific and the Reserve Bank of New Zealand (RBNZ).

Quyen Nguyen is the STRAND Marsden Fund Project Postdoctoral Fellow (2021–2024) hosted at the Climate & Energy Finance Group (CEFGroup), Department of Accountancy & Finance, University of Otago. She is the principal modeller for the STRAND Marsden Fund Project entitled "Should I stay or should I go? Climate-change risks to property values across space and time, and the related implications for financial stability". Quyen is also working with EMMI on applying machine learning techniques to predict and forecast corporate carbon footprints. Quyen obtained her PhD on Essays on Climate Finance Transition Risks (2018–2021) at the University of Otago. She also holds a BA in International Business Economics and an MBA (focused in finance) from the University of Minnesota. Prior to moving into academia, Quyen worked in a number of finance, risk management and business analytics roles for Intel, Pfizer and a US healthcare start-up. Her current teaching and research interests are mainly in climate finance & data science.