Instructors:

      Adriano Morales, University of Twente, The Netherlands

      Abdulaziz Yusuf Ali, University of Twente, The Netherlands

Short description

This course introduces participants to sustainable finance through the lens of spatial data, spatial statistics, and machine learning. It begins with an overview of climate finance and spatial finance, emphasizing how asset locations, environmental hazards, and geospatial information can be combined to assess physical and transition risks. Participants will then explore key spatial statistical methods, including geostatistics, Bayesian modelling, and spatial point processes, with applications to housing prices and climate risk, deforestation and asset exposure, hazard-related losses, and transport emissions.

Materials > Download    

Instructors:

Adriano Morales, University of Twente, The Netherlands

Abdulaziz Yusuf Ali, University of Twente, The Netherlands

Short description

The second part of the course focuses on ESG and financial materiality, showing how spatial data can support the identification, measurement, and interpretation of financially relevant sustainability risks. Machine learning methods for spatial classification and clustering will also be introduced, with examples related to deforestation and mining mapping, rooftop damage classification, environmental risk mapping, and broader asset-level exposure assessment. The course combines conceptual lectures with hands-on laboratory sessions in which participants apply spatial and machine learning tools to develop risk maps and classification outputs.

Evening session

Laboratory lectures – supervised tutorial, individual and team work.

Materials > Download     

Instructor:

Dimitris Karlis, Athens University of Economics and Business, Greece

Short description

This course introduces the basic ideas and principles of dimension reduction. It focuses on Principal Components Analysis, including the underlying methodology, the choice of the number of components, variants of the method, and applications with real data.

Evening session

Laboratory lectures – supervised tutorial, individual and team work.

Materials > Download 

Instructor:

Professor Ioannis Ntzoufras, Department of Statistics, Athens University of Economics and Business, Greece

Short description

This lecture introduces the fundamental principles and methods for analysing survey data in the context of sports sustainability. Using data collected from spectators attending a match between the Greek National Football Team and the National Team of Ireland, participants will explore how survey analytics can be used to understand mobility patterns, transportation choices, and environmental attitudes among football fans.

The course demonstrates how survey data can provide valuable insights into spectator behaviour and its environmental impact. Particular emphasis will be placed on estimating the carbon footprint associated with match attendance, with a focus on travel-related emissions and the role of sustainable mobility practices.

All analyses will be conducted using R. Starting from descriptive and exploratory analytics, participants will learn how to summarise and visualise fans’ attitudes towards sustainability, identify key mobility trends, and quantify the environmental impact of spectator travel. The course will then progress to more advanced analytical approaches for estimating the overall carbon footprint of the event and assessing factors associated with environmentally responsible behaviours.

By the end of the lecture, participants will have gained practical experience in managing and analysing survey data, interpreting sustainability-related indicators, and producing evidence-based assessments of the environmental impact of major sporting events.

Evening session

Laboratory lectures – supervised tutorial, individual and team work.

Materials > Download      

Instructor:

Associate Professor Liana Stanca, Babeș-Bolyai University / FinTech LivingLab

Short description

This lecture introduces the fundamental principles and practical methods of applying Machine Learning and Artificial Intelligence in the context of sustainable finance and ESG-driven decision-making. Using real-world financial and sustainability datasets, participants will explore how data-driven approaches can be used to understand ESG performance, climate risk exposure, and sustainability-related financial indicators across firms and markets.

The course demonstrates how machine learning models and visual analytics can support evidence-based sustainability assessment in finance. Particular emphasis is placed on the integration of predictive modelling and interactive data visualization for ESG analysis, including the development of dynamic dashboards for exploring sustainability metrics, carbon exposure, and financial performance relationships.

All analyses will be conducted in R/Shiny or Python, depending on the implementation, combining exploratory data analysis, machine learning techniques, and interactive visualization tools such as Shiny, Plotly, or Dash. Starting from descriptive analytics and data visualization, participants will learn how to summarize and interpret ESG indicators, identify sustainability patterns across firms, and visualize key financial and environmental relationships through interactive dashboards.

The course then progresses toward supervised and unsupervised learning methods for ESG risk classification, sustainability profiling of companies, and clustering of firms based on environmental and governance characteristics. A dedicated component is included on explainable AI techniques to ensure transparency and interpretability of machine learning outputs in financial decision contexts.

By the end of the lecture, participants will have gained hands-on experience in building and interpreting machine learning models for sustainable finance, designing interactive dashboards for ESG data exploration, and producing data-driven insights that support sustainable investment and risk assessment decisions.

Evening session

Laboratory lectures – supervised tutorial, individual and team work.

Materials > Download