What is ESG Reporting?

Leveraging Data Science for Comprehensive and Effective Environmental, Social and Governance reporting of a company

What is ESG Reporting — (Image by Author)

Environmental, Social and Governance (ESG) reporting is a method used by companies to disclose their governance structures, societal impacts and environmental footprint.

ESG Pillars Presentation — (Image by Author)

As stakeholders increasingly demand corporate social responsibility (CSR), ESG reporting has become critical to companies’ long-term strategies.

As a Data Scientist, how can you support your organization in improving its ESG score with analytics?

In this article, we will delve into the details of ESG reporting to highlight the challenges associated with it and explore how data analytics can improve its accuracy.

📘 Your complete guide for Supply Chain Analytics: Analytics Cheat Sheet
💌 New articles straight in your inbox for free: Newsletter

Summary
I. Understanding ESG Reporting
1. What is ESG Reporting?
2. ESG Reporting supported with Data
II. Advanced Analytics for ESG Reporting
1. Lack of Standardization
2. Accuracy and Reliability of ESG Data
3. Fighting Greenwashing with Data Science
III. Data Science as a Game Changer
1. Sustainable Sourcing
2. ESG-Friendly Budget Planning
3. Supply Chain Network Optimization
4. Circular Economy for Fashion Industry
IV. Conclusion
Open the window on Business Intelligence and Sustainable Development Goals
1. Business Intelligence to Automate the Process
2. Beyond ESG, Towards Sustainable Development Goals (SDGs)

I. Automate ESG Reporting with Data Analytics

What is ESG Reporting?

ESG reporting is a form of non-financial reporting where organisations communicate their environmental performance (E), social responsibility (S), and governance structures' strength (G) to their stakeholders.

These three dimensions provide an in-depth understanding of a company’s sustainability and ethical impacts.

Example of Reporting Categories — (Image by Author)

For instance, a company might report the

• Carbon emissions of its supply chain (E)
• Initiatives for community development (S)
• Diversity of its board members (G)

Let’s look at this reporting from the data analytics point of view.

ESG Reporting Supported with Data

We can consider a hypothetical global fashion retailer: I&N.

I&N is a fast fashion retailer producing garments, bags and accessories in factories located in Asia.

Supply Chain Network of I&N — (Image by Author)

Stores (located in Europe) are delivered from local warehouses that are directly replenished by factories.

I&N is committed to sustainable practices (circular economy, renewable energy) and aims to build trust with its stakeholders through transparency.

Therefore, it regularly discloses its ESG performance in its annual sustainability report.

In its latest report, I&N discloses a number of key ESG metrics

I&N ESG Metrics — (Image by Author)

(E): For the environmental segment, I&N reports

• The total greenhouse gas emissions (kg CO2eq)
• The percentage of energy usage from renewable sources (%)

These indicators, which require advanced data processing, allow stakeholders to understand

• The environmental footprint of the products sold.
• The efforts to transition to cleaner energy sources.

Product Life cycle assessment (LCA) is a data-driven methodology that can be used to evaluate these environmental impacts from a product point of view.

The idea is to analyze each process from raw material extraction to product disposal.

Life Cycle Assessment — (Image by Author)

For each process, we have a look at the

• Consumption of natural resources, raw materials and energy
• Emissions of pollutants and CO2
• Waste generated

💡 For more details about these analytics solutions,

What is a Life Cycle Assessment? LCA

Supply Chain Sustainability Reporting with Python

(S): For the social component, the company details

• The number of community development initiatives it has launched
• An average employee satisfaction score indicates the well-being of its workforce.

How does our company disclose the average employee satisfaction score?

Organizations traditionally rely on surveys to obtain this metric, which can often yield subjective and biased results.

Therefore, I&N decided to use Natural Language Processing (NLP) and Social Sentiment Analysis to analyze text data from employee reviews on platforms like Glassdoor or internal communication channels.

Social Media Sentiment Analysis — (Image by Author)

It can also be used on social media.

ESG sentiment analysis is a valuable tool used by investors to track the mood of stakeholders towards ESG issues and understand how these factors may impact a company’s stock price.

There are tools in the market that perform audits on social media and job platforms.

They employ advanced NLP techniques to get the perspectives of customers and employees on critical topics linked to a company.

(G): For the Governance domain, I&N discloses

• The number of independent board members
• The percentage of female representation on its board.

This helps auditors and investors assess the I&N’s commitment to fair and responsible governance.

Board Composition Analysis is a data-driven evaluation of the diversity and experience of the board members and the management.

This could be done by analyzing data linked to selected managers considered key for the company's strategy.

Example of dummy data for Board Composition Analysis — (Image by Author)

For instance, visuals can be built to analyze workforce diversity using ethnicity distribution.

Ethnicity Distribution Example — (Image by Author)

If I&N wants to promote gender equality, we can analyze the department distribution of male and female managers.

Gender Distribution Example — (Image by Author)

These visuals help identify potential areas of improvement and make a strong case for diversity and inclusion, which is a key aspect of good governance.

In the next section, we will see how advanced analytics can help companies overcome the challenges of ESG reporting.

💡 Follow me on Medium for more articles related to 🏭 Supply Chain Analytics, 🌳 Sustainability and 🕜 Productivity.

II. Advanced Analytics for ESG Reporting

ESG reporting can be complex due to the lack of standardization in reporting practices and the difficulties in ensuring data accuracy.

Lack of Standardization

The first is the lack of standardized reporting frameworks, which can lead to inconsistencies in how different companies report their ESG performance.

For example, two companies may measure their environmental impact in completely different ways

• Company 1 is a plastic toy manufacturer
• Company 2 sells fresh fruits in convenience stores

These two companies report plastic usage reduction

• -55% for company 2 by using carton packaging for some items
• -10% for company 1 by changing the design of toys

However, how can you evaluate the effort and impact while the first company uses plastic as a raw material for its products?

💡 How can data analytics support standardization?

• Governmental entities can use databases of companies by industry and the environmental aspect of their products (Example: World Bank Database)
• Automated data pipelines can extract, process and deploy standardized reports using data from different sources.

Now that you have a standard for your report, you must ensure that the data used is reliable.

Accuracy and Reliability of ESG Data

Maintaining quality can be arduous, with data coming from many sources.

Business Intelligence (BI) provides capabilities to process and analyze large volumes of data from different systems to support ESG reporting.

• Flat files from external suppliers, utility bills or operational files
• Manufacturing data from factories’ management systems
• Logistics and retail operations data from ERPs, WMS and TMS

Analytics Capacitibilities Needed for Life Cycle Assessment — (Image by Author)

In the example above, this data architecture is used to extract, process and store data to perform a Life Cycle Assessment.

The idea is to estimate the impacts of an item sold by

• Linking production outputs quantity with energy and resource usage
• Estimating CO2 and pollutant emissions from production to transportation
• Including additional non-financial indicators from suppliers and logistic operations

The ultimate goal is to automate the calculation of ESG indicators along the life cycle of products from raw materials extraction to disposal.

💡 Additional Insights
This can also support the traceability of the data used for your report.

For instance, I have implemented a system using file hashing to prove that a data source (from a freight forwarder) has not been modified in the process of CO2 emissions calculations.

As you may be audited, showing data sources and proving that results have not been manipulated is important.

Fighting Greenwashing with Data Science

Greenwashing is the practice of making misleading claims about the environmental benefits of a product to communicate a false image of sustainability.

Five sins of greenwashing — (Image by Author)

Organizations use this dishonest practice to create a false impression of environmental responsibility.

However, data analytics can be a great boost to automate fraud detection by using

• Publicly available data in sustainability reports, social media
• Advanced analytics models, including NLP, forecasting or statistical models for fraud detection

💡 For more details about data analytics,

What is Greenwashing? And How to Use Analytics to Detect It?

💡 Follow me on Medium for more articles related to 🏭 Supply Chain Analytics, 🌳 Sustainability and 🕜 Productivity.

III. Data Science as a Game Changer

Beyond measuring and reporting, these technologies can help your organization use the data generated by systems to get

• Prescriptive insights to support decision-making: select a supplier, budget allocation, supply chain network design
• Predictive analytics to help firms anticipate and mitigate future ESG risks

Example 1: Sustainable Sourcing

This is the process of integrating social, ethical and environmental performance factors when selecting suppliers of products or services.

Use Data to Assess Your Suppliers — (Image by Author)

For each supplier, I&N has a set of scores measuring

• Usage of natural resources (water, cotton)
• Pollutants and CO2 emissions
• Social and governance compliance

With advanced analytics, you can automate the full process of

Select a supplier in three steps — (Image by Author)

• Collection of data from suppliers
  Example: sustainability KPIs (CO2, natural resources, Environmental Footprint), social and governance indicators
• Suppliers' assessment based on ESG and business indicators
  Example: fixed and variable costs, quality, social responsibility
• Decision-making using linear programming
  Example: decide the set of suppliers that minimize the profit while respecting minimum levels of ESG scores

This is a real game changer as it can support procurement teams to align their sourcing strategy with the company's ESG roadmap.

💡 For more details about analytics for sustainable sourcing,

What is Sustainable Sourcing?

Example 2: ESG-Friendly Budget Planning

Linear programming can also help you direct your investments in projects that will help support the company’s ESG roadmap.

Let us imagine the scenario of the budget allocation of an international logistics company.

A Regional Director receives budget applications from 17 warehouse managers for projects impacting the next three years.

Example of Budget Planning for a Logistics Company — (Image by Author)

For each budget application, the manager includes

• A description of the project (equipment purchase, renovation, …)
• Yearly budget for the next three years
• Return On Investment = (Cost Reduction + Additional Turnover) — (Total Cost)
• Additional benefits impacting business development, productivity or ESG indicators

Our director must decide which project(s) to allocate her budget based on the financial aspect (ROI) and ESG criterion.

How to maximize the Return On Investment while meeting ESG requirements?

With linear programming, we can automate selecting the projects that will maximize the ROI while respecting constraints on CSR, HSE or sustainability.

Decision-Making Process — (Image by Author)

• Parameters: boolean values for each project (1: selected, 0: not selected)
• Constraints: business development and ESG benefits
• Objective function: maximize the ROI

By putting the ESG targets set by the top management, our director can ensure that the projects selected will support the company’s long-term strategy.

💡 For more details about ESG-friendly budget planning,

Automate Budget Planning Using Linear Programming

Example 3: Supply Chain Network Optimization

A great way to improve your ESG score is to boost your green and ethical transformation.

Sustainable Supply Chain Optimization is an exciting approach combining cost-effectiveness with sustainability.

Sustainable Supply Chain Optimization Problem — (Image by Author)

You have,

1. Demand for each market location in (Units/Month)
2. A set of potential manufacturing sites with different production costs, environmental impacts, social and governance scores
3. Constraints on environmental footprint per unit, social and governance scores

What is the most sustainable (and economically viable ) combination?

With advanced analytics, you can design a tool to test several scenarios

• What if I want to minimize costs?
  Can I meet my ESG targets?
• What if I want to minimize CO2 emissions?
  Can I keep my profitability level?

Compare different scenarios — (Image by Author)

I have implemented such a model on a web application deployed online:

1. Upload your market demand data (Units) per Market
2. Add your manufacturing footprint data: factories by location with (costs, CO2 emissions, resources Usage and Social Scores)
3. Select the objective function: minimize the cost, CO2 emissions or resource usage

Three scenarios with different objective functions — (Image By Author)

You can quickly switch from one objective to another to decide the most viable solution.

💡 If you want to try this tool, I have shared a POC accessible online

Sustainable Supply Chain Optimization App — (Image by Author)

Example 4: Simulation of a Circular Economy

A circular economy is an economic model that aims to minimize waste and maximize resource efficiency.

Subscription model of a circular economy — (Image by Author)

Some companies have implemented a subscription model where customers pay a regular fee to access a product or service for a specific period.

A customer would like a dress for 2 weeks

• The dress can be picked up at a store
• The item is used for two weeks
• The customer returns the item that is then collected
• After collection, the item is inspected and cleaned before shipping it back to the store

Parameters for the case study — (Image by Author)

Thus, a dress manufactured 1 time can be used by several customers.

By how much can we cut CO2 emissions using this model?

I developed a simulation model based on sales data that estimated the CO2 savings for different rental periods.

Results of the study — (Image by Author)

The results are astonishing,

• -75% of reductions for short rental periods
• Long rental periods affect the efficiency of the network

💡 For more details about this study,

How Sustainable is Your Circular Economy?

These examples gave you an idea of how data analytics can help you improve ESG reporting and reach the targets fixed by your top management.

III. Conclusion

As ESG reporting becomes increasingly prevalent, the role of data analytics in enhancing its accuracy and efficiency is set to grow.

The future may see the development of advanced solutions tailored specifically for ESG reporting.

Business Intelligence to Automate the Process

Business Intelligence is a process that leverages software and services to transform data into actionable intelligence supporting decision-making.

Business Intelligence in 5 Steps — (Image by Author)

These solutions could automate the ESG reporting process, from data collection to analysis and decision-making.

💡 For more information

• What is Business Intelligence?, Samir Saci, Towards Data Science

What is Business Intelligence?

By leveraging these tools, companies can improve their ESG reporting and gain valuable insights to drive their sustainability strategies.

Beyond ESG, Towards Sustainable Development Goals (SDGs)

The Sustainable Development Goals (SDGs) are a set of 17 objectives established by the United Nations to address global challenges.

17 goals that can be grouped into 5 categories — (Image by Author)

Integrating these goals into our operational frameworks is a moral imperative and a great opportunity to boost innovation and efficiency.

Advanced Analytics Tools for People-Oriented Initiatives — (Image by Author)

With data analytics, we can support the design and implementation of initiatives that support these 17 goals and will boost your ESG score.

To dive into my insights about how Data Analytics can support it,

What are the Sustainable Development Goals? (SDGs)

About Me

Let’s connect on Linkedin and Twitter, I am a Supply Chain Engineer using data analytics to improve logistics operations and reduce costs.

If you are interested in Data Analytics and Supply Chain, have a look at my website

Samir Saci | Data Science & Productivity

💡 Follow me on Medium for more articles related to 🏭 Supply Chain Analytics, 🌳 Sustainability and 🕜 Productivity.

References

• Automate Budget Planning Using Linear Programming, Samir Saci, Towards Data Science
• What is a Life Cycle Assessment?, Samir Saci, Towards Data Science
• Supply Chain Sustainability Reporting with Python, Samir Saci, Towards Data Science
• Sustainable Supply Chain Optimization App, Samir Saci, Access the APP
• What is Sustainable Sourcing?, Samir Saci, Medium
• Sustainability Accounting Standards Board (SASB), SASB
• UN Principles for Responsible Investment (PRI), United Nations
• CDP (formerly Carbon Disclosure Project), CDP Worldwide