Discover team Green Finance Lantern's innovative solution- shared by their mentor, Miles Elliott: *EY France, under the sponsorship of Franck Chevalier, Nathanael Sebbag and Antoine Helouin, elected to enter this year's 2025 SAS Hackathon.  The team, under the operational management of Christophe Beaugendre, identified the topic of linking Biodiversity Risk to Corporate Credit Risk.  In this short paper we will explore what was done, why and what were the key outcomes.  Specific credit goes to the work of AI & Data, ESG and sustainability teams from EY France*   In finance, biodiversity often appears as an abstraction—something beautiful yet detached from balance sheets and credit models.   The Lantern Project set out to change that. Over an intense few weeks during the SAS Hackathon, this team demonstrated how the loss of pollinators—tiny, tireless agents of ecosystem health—can translate into quantifiable financial risk.   As a mentor on this project, I had the privilege of guiding a group of innovators who transformed a complex sustainability concept into a working data-driven prototype. The journey from idea to insight revealed not only technical creativity but also a glimpse of what nature-positive finance might look like in practice.   Defining the Challenge: Making Biodiversity Financially Visible The team began with a deceptively simple question: Can biodiversity loss be measured as a financial variable?   More specifically, could we model how variability in pollination—an ecosystem service essential to many crops—affects agricultural production and, ultimately, the creditworthiness of farmers? Increasingly, financial regulators and institutions are asking how natural capital risks might materialize on balance sheets. Pollinator variability, being both measurable and economically relevant, provided a tangible entry point.   Our goal was to build a proof of concept that would: Quantify the relationship between pollination and farm-level yields; Translate those yield effects into credit risk metrics, such as the probability of default (PD); Present these insights through a SaaS-powered dashboard capable of guiding lending decisions.   Framing the Data Strategy Early in the process, the team realized that data would make or break the entire model. Biodiversity is inherently spatial—it happens in fields, not spreadsheets. So our data architecture needed to merge geospatial ecological datawith financial data at the level of individual farms.   We began with publicly available sources: The French Agricultural Parcel Registry (RPG): a detailed dataset covering roughly 140,000 plots in the PACA (Provence-Alpes-Côte d’Azur) region. Each plot included coordinates and crop types. Ecological data from the Dutch PBL Institute, offering land-cover projections from 2020 to 2050 under different sustainability scenarios (SSP1 and SSP5). Scientific data on crop pollinator dependence, derived from global studies quantifying how yield responds to pollinator availability. Using these, the team constructed a data pipeline that could spatially align and harmonize information at the farming plot level. Each farm was approximated by clustering neighboring plots using a hexagonal grid system, and every plot was assigned a percentage of surrounding land favorable to pollinators. This figure—a measure of pollinator habitat sufficiency—served as the ecological anchor of the model. To ensure privacy and realism, we then used SAS DataMaker to generate a synthetic portfolio of 3,000 farmers, complete with production and financial attributes like assets, debts, and leverage. The synthetic design allowed us to test relationships safely, while maintaining plausible variability.   Designing the Models: From Ecosystem Service to Default Probability Once the data foundation was in place, the next step was to create a modeling framework that could translate ecological stress into financial outcomes.   The modeling pipeline followed three logical steps: Yield Estimation: Using the pollinator sufficiency metric, we estimated how yield would change under different pollination scenarios. For instance, if the share of pollinator-friendly habitat fell from 27% to 12%, sufficiency—and hence yield—might decline by roughly 60%. Revenue and Profitability Projection: These yield changes were then aggregated to the farm level, taking into account each farm’s mix of crops. Farms dominated by pollinator-dependent crops such as apples, melons, or berries showed higher vulnerability than those focused on cereals or oilseeds. Credit Risk Adjustment: The financial model linked projected profitability changes to leverage and default risk, adapting concepts from a 2021 European Central Bank climate stress-testing paper. In simple terms, lower yields lead to lower revenue, which raises leverage ratios and increases the probability of default (PD). Finally, each farmer’s PD under different future scenarios was used to categorize lending decisions: Lend normally (low PD and low change in PD) Lend with conditions (moderate PD increase) Do not lend (high or sharply increasing PD) This categorization bridged environmental and financial analytics in a single decision framework—a crucial step toward nature-aware lending.   The Role of SAS and AI All this analysis was orchestrated within the SAS Viya platform, which handled data ingestion, transformation, and modeling at scale. The team also prototyped a large language model (LLM)-powered decision tree to automate recommendations—essentially an AI loan officer that considers both environmental and financial parameters.   An interactive dashboard displayed every farm as a point on the map, color-coded by size and PD impact. Users could drill down into each holding to see: Crop composition Pollinator habitat metrics (2020 vs. 2050) Yield projections and financial indicators Lending recommendations This visual synthesis made the complex interplay between biodiversity and finance immediately tangible for bankers, risk analysts, and policymakers.   Insights and Outcomes One of the project’s most striking findings was its selective impact. Out of 140,000 plots analyzed, only about 24,000 (roughly 500 farmers) faced meaningful pollinator habitat decline. However, for those affected, the financial consequences were significant—particularly when high dependency crops dominated their portfolio. The implication is clear: biodiversity risk is localized but material. Financial institutions equipped with such insights could tailor credit terms, prioritize resilience investments, or offer transition finance to at-risk farmers. Beyond the numbers, the Lantern Project proved something more profound: that nature’s value can be expressed in financial terms without diminishing its essence. When biodiversity enters the credit model, sustainability shifts from a moral imperative to a measurable factor in economic resilience.   Reflections on Mentorship and Collaboration From a mentor’s perspective, what stood out most was the team’s willingness to cross boundaries. Data scientists learned to read ecological maps. Finance analysts debated spatial modeling. Sustainability experts interpreted default probabilities. This spirit of interdisciplinary fluency turned a theoretical problem into a functioning prototype—one that hints at the next generation of ESG analytics.   Looking Ahead Lantern is just the beginning. The same architecture could be extended to other ecosystem services—water retention, soil health, or carbon storage—and across other regions. By embedding natural capital into financial models, we can begin to design credit systems that reward resilience, not just yield. In doing so, we move a step closer to aligning finance with the planet’s true balance sheet.   - Miles Elliott   A huge thank you to our sponsors, Intel and Microsoft, whose support made this Hackathon possible. Their contributions went far beyond sponsorship- bringing expertise, resources, and inspiration that fueled innovation. Together, they created a truly collaborative and transformative experience for all participants.   Green Finance Lantern is just one of many visionary teams from this year’s Hackathon. Find out who the champions are during our award session Dec. 11 on YouTube and LinkedIn! ... View more

Discover team Matadori’s innovative solution- shared by their mentor, Ulrich Reincke:   Europe is in pain—literally. Chronic pain has become a silent epidemic, affecting hundreds of millions of people. If you walk through any European city today, odds are one out of two people you pass suffers from persistent pain in some part of their body. As the Matadori hackathon team explained, “approximately 380 million people across Europe are right now suffering from various pain across their bodies”. From debilitating back pain to sacral joint conditions, the problem is vast, human, and urgent.   The good news: solutions exist. Across Europe, specialized medical centers are capable of treating these patients and dramatically improving their quality of life. But technology has not yet solved an essential challenge—connecting the right patients to the right specialists at the right time. As the team summarized, patients today face a major barrier: “The right patient that is suitable for these procedures needs to find the right doctor” .   That challenge became the mission for the Matadori team, three former classmates from Czech University of Life Sciences Prague in Prague who joined the SAS Hackathon while juggling full-time jobs. With limited time, no formal SAS training, and a complex healthcare problem, they chose not to aim small. They set out to build an intelligent system capable of predicting which patients could benefit most from advanced pain-relief treatments—based on electronic medical intake questionnaires.   The Problem: A Digital Bottleneck in Patient Care Most pain-treatment clinics today rely on extensive e-consultation surveys. Each submission includes detailed medical history, pain characteristics, duration, location, and severity. These questionnaires are essential, yet time-consuming: clinicians must manually interpret each one to determine whether a patient is a good candidate for a procedure.   The Matadori team recognized this as both an inefficiency and an opportunity. If machine learning could pre-screen patients, physicians could focus their time on those most likely to benefit—accelerating treatment and improving care at scale.   But there was a second insight too: this model could guide search engine optimization and digital outreach. In the team’s words, the same insights could be used to “find the right patient for the procedures by targeting in the online environment, especially through search engine optimization” . In other words, identify patients algorithmically—and reach them before they even request a consultation.   Building a Model Under Pressure Short on hackathon time, the team worked evenings, compressing months of modeling work into days. Yet speed didn’t force compromise—it sparked creativity.   Their modeling pipeline was textbook data-science rigor: “We start with the raw data, followed by an imputation step to handle missing values. Then we built multiple predictive models… including logistic regression and several gradient boosting models… and select the champion model.”   Through SAS Viya’s no-code/low-code interface, they built and compared multiple algorithms, ultimately choosing an ensemble method. To optimize clinical usefulness, they also adjusted the decision cutoff to ensure the model prioritized precision: “We adjusted the binary cutoff to 85%, which makes the model more specific… reducing false positives, and ensuring that only highly relevant cases are flagged for doctors” .   This decision was not technical—it was ethical. In healthcare, incorrectly approving patients is more dangerous than rejecting borderline cases. The team aligned the model to real clinical risk.   Understanding Who Needs Help Most With the champion model selected, the team then asked: What features matter most for predicting patient suitability? The model revealed three dominant predictors: “Body Area Score… pain intensity, and pain duration” .   Patients reporting neck, trapezius, and upper-back pain—often caused by modern desk work—were especially strong candidates. Persistent lower-back conditions also played a major role, reflecting known clinical patterns. And unsurprisingly, the longer a patient had been in pain, the more likely they needed intervention.   This wasn’t only a clinical breakthrough; it was a digital strategy one. With this knowledge, the team could create search engine optimization content targeted directly to the most at-risk individuals—helping more people find expert care sooner.   The Power Behind the Innovation: Synthetic Data While the modeling work was impressive under time pressure, the quiet hero of this project was data. Healthcare data is sensitive and protected—and for good reason. It contains deeply personal medical history. Traditionally, that limits collaboration, innovation, and experimentation.   But not this time.   The team started with real patient records and generated synthetic examples using SAS Data Maker. As they described: “We had 10,000 synthetic data made from the 5,000 original data… this helped us make a great model… trained on the 10,000 synthetic data and then validated on the original data” .   This is the future of AI in medicine.   Synthetic data unlocked three critical advantages: Privacy by design – No real patient identity was exposed, maintaining compliance and ethical standards. Data volume expansion – Doubling the dataset created better model training conditions. Rapid iteration and validation – Models were safely trained on synthetic data and then verified on real-world patterns.   In other words, synthetic data gave the team speed, security, and scale—without compromise. This approach demonstrates how SAS technology enables responsible AI in regulated industries. It also highlights why synthetic data is becoming a fundamental fuel source for advanced analytics. As privacy laws tighten, healthcare providers, governments, and enterprises need data that behaves like reality without being reality. Tools like SAS Data Maker make that not only possible but intuitive.   Why Synthetic Data Matters for the Future of Healthcare The Matadori solution is a snapshot of what's coming. Healthcare systems everywhere are shifting from reactive to proactive models. Instead of waiting for patients to deteriorate, technology helps anticipate needs and route individuals to care early.   Synthetic data is critical to achieving this vision. It unlocks: Faster innovation cycles without waiting for real clinical datasets Stronger privacy protection that builds trust with patients and regulators Bias reduction by generating balanced datasets where under-represented groups are amplified Scalable simulation environments to test scenarios clinicians may rarely encounter   In this hackathon, synthetic data delivered tangible wins: A robust model trained safely and ethically Clinically relevant predictions aligned with medical logic Predictive intelligence paired with digital-outreach capabilities Validated model performance on real-world patterns   This is the blueprint for modern healthcare AI: privacy-preserving, clinically aware, fast-to-deploy, and explainable.   From Hackathon to Impact Innovation often requires constraint. Limited time, no deep SAS training, and complex clinical data could have slowed the team down. Instead, they accelerated. As they put it, even working evenings after their day jobs: “We were amazed at how quickly… we can develop these complex models… and validate them in the SAS Viya platform in just a few clicks” .   In a matter of days, the team built a sophisticated patient-triage system—and a digital-engagement strategy to get it in front of people who need it most.   For me, as a mentor, this was a powerful reminder: when talented people are given the right tools and a meaningful problem, they move mountains. Or in this case, they reduce pain across a continent. Their work is not just a hackathon success story. It's a vision for how AI, responsibly powered by synthetic data, will transform care pathways, reduce system burden, and improve lives.   And most importantly, this solution isn't theoretical. It is ready to scale.   - Ulrich Reincke   Matadori is just one of many visionary teams from this year’s Hackathon. Find out who the champions are during our award session Dec. 11 on YouTube and LinkedIn! ... View more

Innovation often starts with a spark, but real progress comes when people come together to turn ideas into action. That’s exactly what is happening at the very first Benelux HackSprint, a three-day in-person event powered by the SAS Hackathon and brought to life through the vision and drive of Ilanite Keijsers and Nick Tjintjelaar.   From September 23–25 at the KNVB Campus in Zeist, multidisciplinary teams will gather to collaborate face-to-face, experiment with AI-driven solutions, and tackle pressing challenges in sustainability, healthcare, mobility, and beyond.   On the eve of the event, we asked Nick about the thinking behind the HackSprint, how it came together, and what he hopes to see emerge.   What inspired the HackSprint in the first place? The SAS Hackathon is already a powerful platform for innovation, but we wanted to add a local, in-person dimension to accelerate progress, build stronger relationships, and spark creativity. A concentrated three-day sprint gives teams the chance to step away from screens, meet in person, and transform early concepts into working prototypes. The idea is not only to boost the Benelux Hackathon but also to create a blueprint that other regions can adapt in their own way.   How did you go about bringing this event to life? It started with vision, but quickly became about execution. We chose the KNVB Campus in Zeist — an inspiring location in the woods — as the perfect setting for collaboration. We invited 6–10 multidisciplinary teams of partners, customers, universities, and research centers, each with 5–8 members. SAS will cover all logistics, from hotels to meals, so teams can focus entirely on innovation.   Importantly, the HackSprint is fully aligned with the global Hackathon nomination and recruitment process. That means it’s not a separate effort, but a seamless extension of the global program.   What makes the HackSprint unique compared to the Hackathon itself? The HackSprint acts as a midway motivator. Teams will already have started their Hackathon journey, but Zeist offers a chance to test frameworks in real time, gain feedback from mentors, and energize their efforts. Unlike the remote setting of the Hackathon, this is about rapid, face-to-face prototyping. At the end of three days, all teams will present their prototypes, and in a peer-driven twist, they’ll vote for the most inspiring sustainability case — with the rule that no one can vote for their own.   What themes will inspire the HackSprint? We’ve drawn inspiration from The Only Planet by Tim van Hattum, which outlines seven natural pathways to a hopeful future, aligned with the UN Sustainable Development Goals. These include regenerative food systems, circular economy, nature as an ally, and urban innovation, among others. Data and AI have the power to accelerate progress across all of these pathways, and the HackSprint is designed to show how.   How are we showcasing the power of data and AI in action? Seven innovative teams are working on use cases across healthcare, sports, food & agriculture, and the public sector. Medicine4Audit – Using LLMs to automate DICA registrations and reduce administrative burden. FC Data Dribblers – Optimizing competition schedules to minimize travel distances and CO₂ emissions. Mount Analytics – Developing smart semantic recognition of table content. REAiHL Lab – Evaluating LLMs to ensure reliable and ethical clinical applications. flowER – Predicting patient flows and orchestrating hospital processes more efficiently. Food & Agri Team – Leveraging data analytics for sustainable solutions in food and agriculture. TrackGPT – Applying Generative AI and text analytics to streamline railway incident reporting.   All these teams will aim to demonstrate how data and AI can drive innovation, reduce inefficiencies, and make processes smarter across multiple domains.     Looking ahead, what do you expect to see come out of this? I expect to see stronger prototypes — tangible solutions that teams can carry into the next phases of the Hackathon. Beyond that, we anticipate new opportunities: deepened partnerships, academic collaboration, and a stronger profile for SAS as a leader in AI and sustainability. And perhaps most importantly, I hope the HackSprint inspires other regions to create their own versions, rooted in local context but aligned with the same spirit of innovation.   Seven teams. Three days. One inspiring sprint. The Benelux HackSprint begins tomorrow. ... View more

Imagine a world where nature and technology work hand in hand to combat climate change. Sounds like a dream, right? Well, Tim van Hattum, Program Leader Green Climate Solutions at Wageningen University & Research, believes this dream is within our grasp. In his inspiring book, The Only Planet, Tim takes us on a journey through our past, present, and the crucial steps we need to take for a sustainable future. With nature at the heart of his vision, he outlines seven exciting pathways filled with practical tips and hopeful solutions. It's a breath of fresh air amidst the usual doom and gloom we hear daily. Tim was one of the keynote presenters at SAS Innovate in Antwerp and that gives me to chance to ask him a few questions.   A Vision for a Greener Future Question: Tim, how does your vision resonate to the generation of tomorrow?   The upcoming generation craves a cleaner, greener, and more connected world. The book is like a trusty guide, offering a clear roadmap to a livable future that anyone can start following today. We're on the brink of the most thrilling adventure humanity has ever faced—a journey towards a greener future on our 'only planet.' Climate change and biodiversity loss are the big challenges of our time. Lately, we've been swamped with scary images of floods, droughts, and wildfires, which can be pretty overwhelming. But here's the thing: we don't have time for despair. It's time to roll up our sleeves and get to work. The good news? Most of the solutions we need are already available. Never before in the worlds history we’ve had access to so much knowledge, solutions and financial means to solve this global crisis. The key is to balance our society with nature. By teaming up with nature and using smart technology on a large scale, we can create a hopeful future. Question: The book takes you on a journey through seven pathways, showcasing inspiring examples from around the world and proving that this transition is already happening. Can you explain how these seven pathways interconnect and if there is a role for data and AI? Data and AI play a crucial role to accelerate the journey through the seven pathways. All pathways are interconnected, and a healthy biosphere is the foundation for all of them.   The Seven Pathways Nature as an Ally: Let's make nature our partner in fighting climate change. An example is AI-driven models to identify and optimize areas for reforestation and biodiversity conservation. Blue gold: Innovative ways to manage and sustain our water resources. An example is Smart water distribution systems using predictive analytics to minimize waste. Regenerative Food Systems: Revolutionizing how we produce and consume food sustainably. An example is Optimizing crop yield and reducing food waste using machine learning. Urban Innovation: Building smarter, greener cities for everyone. An example is Models for optimizing green spaces to enhance urban health and biodiversity. Energy & Mobility: Powering our lives with renewable energy and sustainable transport. An example is EV charging station optimization for cities and rural areas. Circular Economy: Cutting waste and making the most of our resources. An example is predictive analytics to optimize product life cycles and recycling efforts. Health & Happiness: Living sustainably for a healthier, happier life. An example is AI-powered mental health tools for public welfare initiatives. This framework will be the backbone of the hackSprint at the KNVB in Zeist, the in-person experience of the SAS Hackathon. Hacksprint | SAS   Do you want to explore how data and AI can drive meaningful climate action and imagine and build a sustainable future?   Check out the Global Hackathon information here: SAS Hackathon | SAS and watch the Webinars - SAS Hackathon | SAS with all the insights you always wanted to know.   Interested in learning more? Check out Tim's book: Only Planet, Climate guide for the 21ste Century: Seven nature-positive pathways to a hopeful future four our planet: Amazon.co.uk: van Hattum, Tim: 9789461563408: Books Together, we can make a difference! ... View more