Over the past few years, global executives have faced a number of challenges: economic uncertainty, geopolitical conflicts, supply chain disruptions, and the difficulty in attracting and retaining talent, among others. When asked to rank the most pressing issues for their organizations, many CxOs ranked climate change as one of the “top three issues.”
Co-founder & CTO of Coinscrap Finance
Prioritizing sustainability in times of disruption
As stated in the Deloitte report: CxO Sustainability Report. Accelerating the 2023 green transition, companies feel that they need to act now, since alleviating the climate crisis is something that all stakeholders demand, from the shareholders meeting, to the C-suite, including customers and the team:
- 61% said climate change will have a very high impact on their organization’s strategy and operations over the next three years.
- 75% stated that their organizations increased their sustainability investments in the past year, with 20% ensuring they increased very significantly.
- 46% affirmed that ensuring the right transition to a green products and services strategy is extremely important to their organizations.
These concerns regarding the effect of greenhouse gases have motivated the development of certification protocols that calculate the industrial carbon footprint (cf). Until now, these protocols were manual and implied significant costs in working hours and document management.
For example, we currently have Machine Learning-based technology (ml) that generates an analysis of the environmental footprint in real time just by accessing bank transactional data.
A new carbon footprint estimation model
As in other sectors, decision-making sometimes lacks the necessary transparency, especially from the point of view of the end user. In the research that I carried out with my team, summarized in this post, automatic methodologies for the estimation of carbon footprint are presented, taking into account these transparency limitations. Our analysis led to the proposal of a new machine learning solution applicable for automatic carbon footprint calculations through the bank data present in the daily transactions of the users.
Of particular interest is the fact that no previous research has considered the use of bank transaction classification for this purpose. For our classification, different machine learning models were used: Support Vector Machine, Random Forest, and Recursive Neural Networks. The results obtained reached 90% in the evaluation metrics of accuracy, precision and recovery. Based on its decision paths, this proposal manages to estimate the CO2 emissions associated with bank transactions.
Industry needs and medium-term vision
As investors and customers show more interest in sustainable assets, we need to continue to develop technology capable of promoting practices of environmental awareness of banking industry. These tools will assess daily, for example, a portfolio’s exposure to different climate risks, analyze public opinion on sustainability, calculate the positive or negative impact of a company on the Sustainable Development Goals (SDGs) or measure the impact of assets of the company in terms of emissions.
As a result, this is possible because the Fintech ecosystem we belong to is leading the transformation with innovative solutions. We may not forget that we need to fully justify the results so that they are 100% reliable and increase confidence in automatic processes. In future works, we will make the tool available in other languages, expand the corporate information displayed in each transaction and study the impact of hierarchical methodologies in categorization.
A crisis that is turning into an opportunity
“While we don’t always have a map to navigate the unknown, we have a moral compass. We have a lot of work to do, but we can make it. Humanity has never had so much knowledge, resources, and intelligence than it does today to solve these problems.”Juvencio Maeztu, Deputy General Director and Financial Director, Grupo Ingka (IKEA).
“Customers across regions have high expectations for the products they purchase and the companies they choose. ESG metrics are increasingly an important part of their decision-making process. This means looking at circular processes to extend product life.”Mary Jacques, Executive Director of Global ESG and Regulatory Compliance, Lenovo.
The climate crisis is one of the greatest challenges facing humanity today. Companies in all sectors are already taking steps to address this issue and reduce their carbon footprint, just as their end customers are. Undoubtedly, education is key to fostering environmental awareness in banking and insurance sector.
And it is that companies need to provide clear and accessible information about their sustainable practices and products, and educate users on how they can take steps to reduce their carbon footprint by purchasing sustainable products.
In summary, achieving more sustainable finances is only possible if entities already take the necessary measures. They will end up benefiting the planet, brand reputation and long-term profitability. All are advantages!
About the Autor
Óscar Barba is co-founder and CTO of Coinscrap Finance. He is an expert Scrum Manager with more than 6 years of experience in the collection and semantic analysis of data in the financial sector, classification of bank transactions, deep learning applied to stock market sentiment analysis systems and the measurement of the carbon footprint associated with transactional data.
With extensive experience in the banking and insurance sector, Óscar is finishing his PhD in Information Technology right now. He is an Engineer and Master in Computer Engineering from the University of Vigo and Master in Electronic Commerce from the University of Salamanca. In addition, Scrum Manager and Project Management Certificate from the CNTG, SOA Architecture and Web Services Certificate from the University of Salamanca and more.