Bavo DC Campo, a talented data scientist specializing in fraud detection and social network analytics, shares his insights on combating insurance fraud. He discusses how graph techniques reveal hidden links among fraudulent claims and actors. Bavo introduces the BiRank algorithm, akin to Google’s PageRank, which helps prioritize suspicious claims. His innovative iFraud simulator is also highlighted, showcasing its role in training models to detect fraud. The episode underscores the vital role of social networks in identifying patterns and trends in fraudulent activities.

In this discussion, Justin Wang Ngai Yeung, a PhD candidate at the Network Science Institute in London, delves into the intersection of network science and crime. He reveals how graph-based models can uncover key figures in criminal organizations and optimize law enforcement strategies. Key topics include the challenges of inaccurate data, innovative interventions to dismantle networks, and the role of machine learning in revealing hidden connections. Justin also highlights the need for improved data collection methods to better understand organized crime.

In this episode today’s guest is Celine Wüst, a master’s student at ETH Zurich specializing in secure and reliable systems, shares her work on automated software testing for graph databases. Celine shows how fuzzing—the process of automatically generating complex queries—helps uncover hidden bugs in graph database management systems like Neo4j, FalconDB, and Apache AGE. Key insights include how state-aware query generation can detect critical issues like buffer overflows and crashes, the challenges of debugging complex database behaviors, and the importance of security-focused software testing. We'll also find out which Graph DB company offers swag for finding bugs in its software and get Celine's advice about which graph DB to use. ------------------------------- Want to listen ad-free?  Try our Graphs Course?  Join Data Skeptic+ for $5 / month of $50 / year https://plus.dataskeptic.com

Gabriel Petrescu, founder of Evos Innovation and creator of the OrgXO platform, delves into the power of network science in organizational structures. He shares how mapping companies as networks can uncover hidden influencers and bottlenecks that hinder collaboration. As companies shift from rigid hierarchies to interconnected frameworks, Petrescu reveals strategies for identifying overburdened employees and addressing departmental silos. His insights into the practical applications of network analysis promise to transform decision-making and enhance workplace adaptability.

Hiroki Sayama, a SUNY Distinguished Professor and director of the Center for Complex Systems at Binghamton University, shares his expertise on network science in organizational settings. He discusses how organizational network structures affect decision-making and creativity. Hiroki reveals that sparse connections can lead to more innovative ideas than highly interconnected teams. Additionally, he highlights the impact of team size and proximity to leadership on performance, emphasizing the importance of diverse clusters for fostering creativity.

Yoed Kennet, an assistant professor at the Technion, explores the intersection of cognitive and network science to unlock the mysteries of the human mind. He discusses how creativity can be measured through riddles and the importance of network structures in memory. Learn about memory restructuring during insights, the connection between semantic networks and creativity, and real-world applications in workplaces and education. Yoed's innovative research reveals how understanding these cognitive processes can combat rigidity and enhance problem-solving abilities.

Garima Agrawal, a senior researcher and AI consultant, dives into the dynamic synergy between large language models and knowledge graphs. She highlights how knowledge graphs can reduce AI hallucinations and enhance accuracy by integrating domain expertise. They discuss real-world applications, from smarter customer support systems to AI-driven decision-making pipelines. Garima emphasizes the importance of human oversight in AI integration and advocates for a strategic, rather than fearful, approach to adopting these technologies.

Bnaya Gross, a Fulbright postdoctoral fellow at Northwestern University, dives into the intriguing world of network science's applications. He explores how interconnected networks can lead to cascading failures, shedding light on power outages and even biological systems. Key discussions include using network principles to enhance infrastructure resilience and analyzing disease interdependencies for drug repurposing. Gross also unravels the complexities of aging through network models, revealing potential strategies for rejuvenation.

In this insightful discussion, Erwan Le Merrer, a collaborator in graph theory and distributed systems, reveals how graph-based techniques can expose patterns in large language models and shadow banning on Twitter. He explains the application of epidemic models to examine shadow banning spread across user networks. The conversation also highlights the use of graph metrics to audit LLM outputs, the challenge of bias detection in AI, and innovative methodologies for understanding algorithmic behavior, shedding light on often-overlooked platform moderation practices.

Šimon Mandlík, a PhD candidate specializing in machine learning for cybersecurity at the Czech Technical University, dives into the intriguing world of fraud detection using graph-based techniques. He explains how graphs can unveil malicious activities by analyzing relationships within vast datasets. The discussion highlights the advantages of his hierarchical multi-instance learning method over traditional approaches, tackling challenges like scalability and heterogeneous graphs. Mandlík emphasizes the 'locality assumption' in fraud detection, resulting in faster and more accurate outcomes.