With Apache Hop and Neo4j, you can draw valuable insights into your data loading processes, identify where things went wrong, view the detailed logs, and perform root cause analyses using graph queries. In this session, using Apache Hop as a data orchestration tool, we’ll show you how to use Hop to load data into Neo4j. Alternatively, we’ll show you how to use Neo4j to see how data is being loaded into Hop, by storing all the relevant lineage information into a graph.
Join us to understand how you can use graph-native machine learning in Neo4j to make breakthrough predictions. Previously only accessible to researchers and a very few advanced tech companies, Neo4j has democratized graph-based ML techniques that leverage deep learning and graph convolutional neural networks. Most data science models ignore network structure while graphs add highly predictive features to ML models, increasing accuracy and enabling otherwise unattainable predictions based on relationships. With the recent update to the Neo4j Graph Data Science library, anyone can take advantage of this state-of-the-science technique to create representations of your graph’s most significant features for new and more accurate predictions with the data you already have. In this session, we’ll explain our new graph embeddings and demonstrate using the GraphSAGE embedding results with our new ML catalog. We’ll also visualize the predictions of different models using Neo4j Bloom.
La Graph Data Science Library est une bibliothèque d’algorithmes orientés graphes intégrée à Neo4j. Elle comprend des algorithmes de centralité pour mesurer l’influence, de détection de communautés, de recherche de chemins, de calcul de similarité et de prédiction de liens. La Graph Data Science Library intègre des algorithmes à la pointe de la recherche et simplifie leur utilisation en tirant partie de la base de données de graphes Neo4j. Intervenant: Nicolas Rouyer, Senior Field Engineer chez Neo4j [FR]
Traditional fraud prevention measures focus on discrete data points such as specific accounts, individuals, devices or IP addresses. However, fraudsters today have sophisticated ways to get away with using collaborative efforts and synthetic identities. To uncover such fraud rings, it is essential to look beyond individual data points to the relationships between them. Graph data science harnesses the power of connections to analyze data relationships, detect suspicious patterns and prevent fraudulent transactions. Join us for this webinar for a deep dive into graph analytics for fraud detection where we will discuss: - How to use graph data science to prevent fraud - How to improve fraud detection with graph feature engineering - How graph analytics benefit even non-technical fraud investigators Presenters: Amy Hodler, Graph Analytics & AI Program Director, Neo4j Dave Voutila, Solutions Engineer, Neo4j
Learn how Nulli, working with its clients, addresses the latest challenges faced by the modern Identity Access Management world. The realm of access management is expanding to address the increasing number of relationships required to support consumer analytics, employee regulatory compliance, GDPR, ML, IoT and so much more. Nulli applies the power of graph databases to modeling and traversing these sophisticated relationships, allowing access management software to evaluate contextual policy decisions. In this session, Seyed Hossein Ahmadinejad, Senior Identity and Access Management Architect with Nulli - Identity Management, will illustrate solutions supporting this expanded realm of access management. You will learn about the application of graph algorithms to model security roles, as well as the value of graphs when making access policy decisions.
A new study from IBM suggests it takes 206 days on average for companies to discover a data breach and another 73 days to fix it. The slightest lapse in data security could cripple a business. Neo4j’s developers have invested over a decade in graph technology to provide the graph community with the security features needed to protect data, achieve business goals and minimize cost. This presentation will guide you through Security best practices for your Neo4j developments, ensuring your organization correctly mitigates cybersecurity threats and prepares for incident response. We’ll cover most of the Neo4j security features including: - Leveraging Neo4j 4.1 new role-based access capabilities - Working with third party extensions in extremely sensitive deployment - Best practices using Neo4j to store secure data
An Insider’s Guide: Tips and Tricks to Get the Most from Graph Data Science in the Enterprise - Webinar on 12 August 2020 We have just released the Neo4j Graph Data Science (GDS) library 1.3, which now leverages Neo4j 4.x, has over 50 algorithms and includes enterprise features like support for role-based access control and multi-database. With the GDS framework, you get a production-ready platform for data science at an enterprise scale. Watch the recording to learn tips and insider tricks to tune your graph data science work for production scale, consistency and efficiency. We’ll share important information and demo features such as: - Nuanced algorithm parameters like seeding, thresholds and tolerances - Getting your graph transformed into the analytics workspace - The estimate function for better memory management - Role-based access control for fine-grained security - Exporting graphs for version control - Experimenting with alpha tier functions - Implementing your own algorithm with the Pregel API
Find out how graphs can support solving Cyber Security problems! In the first part of this webinar, we will find out what makes graph databases so unique and powerful, and how we can use them to solve complex Cyber Security use cases, such as fake accounts, workloads hacks or application control. In the second part of the webinar, we will demonstrate live how to build a suitable data model and which algorithms best to use to solve the respective problems. And we will provide tips and tricks to answer your questions. Webinar - 6 August 2020
Data is both our most valuable asset and our biggest ongoing challenge. As data grows in volume, variety and complexity, across applications, clouds and siloed systems, traditional ways of working with data no longer work. Unlike traditional databases, which arrange data in rows, columns and tables, Neo4j has a flexible structure defined by stored relationships between data records. We'll discuss the primary use cases for graph databases Explore the properties of Neo4j that make those use cases possible Look into the visualisation of graphs Introduce how to write queries. Webinar - 23 July 2020
Modern machine learning demands new approaches. A powerful ML workflow requires more than picking the right algorithms. You also need the right tools, technology, datasets and model to brew your secret ingredient: context. In his book, Graph-Powered Machine Learning, Dr. Alessandro Negro explores the new way of applying graph-powered machine learning to recommendation engines, fraud detection systems, natural language processing. By making connections explicit, graphs harness the power of context to help you build more accurate, real-time machine learning models. In this interview with the book’s author, you’ll learn more about: - The role of graph technology in machine learning applications. - How graphs provide better context to improve your ML understanding and workflow. - How graph data science enhances four of the most common recommendation techniques: content-based, collaborative filtering, session-based, and context-aware recommendations. - Data modeling considerations for graph-based recommendation engines. - How to approach designing a hybrid recommendation engine that incorporates multiple approaches.
In this webinar, Helena Deus talks about the COVID-19 knowledge graph that Elsevier created by applying text mining techniques on relevant papers. She also discusses why a knowledge graph was used. Shobhna Srivastava discusses Elsevier's Research Citation network. She talks about how the journey of trying to simplify the existing data processing pipeline, to optimise costs, and choose the right solution to the problem opens the doors to other potential use cases and innovation. Graph technology has been applied to the scientific research domain to enhance content discovery.
As economies continue to reopen across much of Europe and North America, many organizations turn to graph technology to help rapidly reconfigure and reset operations. Graphs are perfectly suited for handling connected data, like tracing connections through complex networks. Graphs can also identify complex relationships faster than human-only efforts by combining multiple isolated datasets and identifying missing data points. In this panel discussion with key Neo4j partners, we discuss using graph technology to help organizations balance efficiency and innovation in today’s challenging times.
[FR] Vous disposez de données et souhaitez en extraire de la connaissance et de la valeur, tout cela en temps réel ? C'est tout à fait possible, mais certains défis sont à surmonter : votre base de données transactionnelle pourrait ne pas supporter l'exécution d'algorithmes consommateurs ; et d'un autre côté, si vous isolez votre intelligence artificielle sur une machine à part, vous perdrez le côté temps réel. Comment articuler ces 2 aspects ? Nous vous présenterons une architecture d’analytique orientée événement, qui couple Neo4j, Kafka et la Graph Data Science Library : vos données connectées seront alors exploitées en temps réel et les résultats seront mis à disposition de la base de données transactionnelle.
Today’s government agencies – both at home and abroad – are beset by increasingly complex challenges within a more interconnected and ever-shifting political landscape. The technology solutions that ultimately overcome these challenges must harness the power of data connections. Governments around the world already use graph technology to fight crime, prevent terrorism, improve fiscal responsibility and provide transparency to their citizenry. Often these solutions involve connecting data across different applications or repositories, spanning disparate processes and departments. Join our online event to discover how graph databases have been helping governments to quickly make sense of obscured, divergent data and hear about our popular use cases and customer references. Agenda 10:00 - 10:40 - Graphs in Government - Jim Webber, Chief Scientist, Neo4j 10:40 - 11:20 - POLE Investigations (Persons, Objects, Locations, and Events) for Governments - Tom Geudens, Senior Presales Consultant, Neo4j 11:20 - 12:00 - Intelligence Use Cases for Graph Data - Michal Bachman, CEO, GraphAware 12:00 - 12:15 - Q&A Session
Graph databases are an excellent choice for storing and querying your connected data. They allow you to store information in a logical and complementary way that’s reflective of the domain you’re working in. However, when faced with the questions you’re looking to answer, it may not be immediately obvious that what you’re looking at is a graph question. In this session we will show you tips and tricks for identifying graph-shaped problems. This webinar is for everybody who wants or needs to learn how to spot certain structures in their data and understand if the data you are working with lends itself to working with a graph.
The new normal for IT professionals is working out of home offices. While Neo4j Pre-Sales and Professional Services have always provided remote services, we have recently fine-tuned our remote delivery of workshops, trainings, bootcamps, health checks, expert services and more. We have boosted functionality, with extra conferencing tools, VPN and data security features, while offering more flexible schedules and timelines. In this webinar, Stefan Kolmar will present some of the Neo4j services packages and demonstrate examples of successful implementation and deployment of Neo4j based projects. The webinar will focus on adapting Neo4j services to the needs of today's world, maintaining productivity by enabling virtual teams to implement and deliver projects remotely. Neo4j webinar on 26 May 2020, presented by Stefan Kolmar
Notre système de santé se modernise au travers d'un projet de loi qui fait la part belle au "parcours de soins". Comment arrêter de raisonner par secteur (soins de ville, hospitaliers, médico-sociaux) ? Comment adopter une approche personnalisée et centrée sur le parcours de soins d'un patient en particulier ? Comment décloisonner les données pour une approche globale qui examine les parcours de soins des autres patients atteints des mêmes maladies ? Dans ce webinaire, nous verrons comment utiliser la base de données de graphes Neo4j et l'interface d'exploration et de visualisation Bloom pour visualiser les expériences patient individuelles et agrégées. Nous utiliserons aussi la GRANDstack pour proposer une interface Web qui donne une vision globale sur ces parcours de soins. Au cours de cette démonstration, nous montrerons qu'établir les relations entre maladies, médicaments, diagnostics, parcours de soins, protocoles, etc. grâce aux graphes et à Neo4j permet de créer de la connaissance et de la valeur, en particulier en recensant les traitements les plus efficaces et en les recommandant au moment approprié aux patients qui en ont besoin. [FR]
[FR] Lors de webinaire en partenariat avec Mondeca, nous aborderons des problématiques autour de l'IA. Graphes et Intelligence Economique : L'IA au service de la conformité Christophe Prigent, Directeur Général, Mondeca L'intelligence économique nécessite d'analyser toujours plus de contenus et données depuis des sources hétérogènes. L'IA offre de nouvelles opportunités pour identifier et qualifier les faits, les personnes et les entreprises sur lesquels s'applique cette analyse. Nous allons voir comment la gestion intelligente du contexte (connaissance du métier) et la puissance du graphe permettent d'exploiter la richesse des contenus non structurés. Un exemple d'application métier (détection de risques d'impayés, conformité des tiers) sera proposé démontrant le processus d'extraction et qualification des données au sein de contenus hétérogènes pour alimenter un graphe intelligent moteur de l'application métier. IA en pratique : la Graph Data Science Library Nicolas Rouyer, Avant-Ventes Senior, Neo4j Les librairies d'Intelligence Artificielle et de Machine Learning ne sont pas toujours faciles d'accès ni simples d'utilisation. Les algorithmes de graphes sont disponibles au travers de diverses implémentations, notamment en Python (graph-tool, networkx, RDFLib). Nous vous proposons de découvrir la Graph Data Science Library, intégrée à la base graphe Neo4j. Son API simplifiée et standardisée permet des configurations personnalisées. Elle implémente plus de 40 algorithmes dans 5 catégories : détection de communautés, centralité, similarité, parcours, détection de lien. Les algorithmes de la Graph Data Science Library sont fortement parallélisés et applicables sur des milliards de noeuds. Nous découvrirons son utilisation dans l'analyse de réseaux sociaux.
Graph algorithms are powerful tools, and there’s a lot of excitement about their applications for data science. It can sometimes be difficult, however - especially for those of us who aren’t data scientists - to know how they might be applied to a particular data set or a specific business problem. There are graph algorithms for centrality and importance measurement, community detection, similarity comparison, pathfinding, and link prediction. Which ones should you use on your data, and which ones might be most useful in answering your business questions? In this presentation, we’ll look at a few examples of Neo4j graph algorithms, and see how they can be applied to data and business problems from the banking industry. We’ll discuss what kinds of data are appropriate for different types of algorithms, show how to model and structure data to work with graph algorithms, and run through some real-world scenarios demonstrating the use of graph algorithms on a sample banking data set Webinar with Joe Depeau, Neo4j, April 15, 2020
For more than a decade, Neo4j developers have empowered the graph community to scale for data needs and achieve business goals, all while minimizing cost. Neo4j 4.0, the latest release from the world’s leading graph database, is the next step in those efforts and delivers a whole new level of scalability. The session features Dr. Alessandro Negro, noted graph database author and Chief Scientist at GraphAware, along with Patrick Wall, Director of Product Marketing at Neo4j. During this webinar, GraphAware explores the powerful scalability features of Neo4j 4.0 in a live demo using the COVID-19 Open Research Dataset.
Companies that collect personal data from Californians are subject to stringent regulations and reprimand – and the rest of North America is watching. The new California Consumer Privacy Act (CCPA) is now law and imposes stiff penalties on those that misuse or resell consumers’ private information. Even victims of data leaks face a reputational and financial risk. Join Yasir Ali, CEO and Founder of Predict Data and Nav Mathur, Senior Director of Global Solutions at Neo4j, for this webinar that addresses: - Highlights of the CCPA Regulation and what it means for organizations - Regulatory-overlap between CCPA, GDPR and other regulations - Personal Identifiable Information (PII) - Data Management in the new regulatory landscape - How can you find and track personal data within your organization - What is graph technology and why is it superior for compliance solutions - Key features of a robust privacy compliance solution
• Neo4j is excited to announce the availability of Neo4j 4.0, the most significant release in the graph technology market to date. Built on Neo4j’s proven native foundation, 4.0 enables developers to build applications that maximize productivity and innovation by extending the scale, security and developer agility offered by the world’s most widely-used graph database. This webinar is an exciting opportunity to hear from the Neo4j experts about how this next-gen graph database is sure to transform the graph technology industry. Emil Eifrem, CEO and Co-Founder of Neo4j, Dr. Jim Webber, Chief Scientist, Ivan Zoratti, Director of Product Management and Lance Walter, CMO, will be connecting with our community in this technical session to discuss: • How Neo4j 4.0’s unlimited scalability meets ever-growing data requirements • Building multiple Neo4j databases in a single Neo4j instance • Neo4j 4.0’s new fine-grained security rules.
As creators and users of artificial intelligence (AI), we have a duty to guide its development and application to increase accountability, fairness and public trust. AI systems require context and connections to have more responsible outcomes and make decisions similar to the way humans do. In this webinar, Amy Hodler, Analytics & AI Program Manager at Neo4j, will take us through 10 Tips for Responsible AI and how artificial intelligence (AI) can be more situationally appropriate and “learn” in a way that leverages adjacency to understand and refine outputs, using peripheral information and connections. Amy will discuss how graphs add essential context to guide more responsible AI that is more robust, reliable and trustworthy.
January is National Human Trafficking Awareness Month. While you might be wondering what graph technology has to do with trafficking, we’ve found that similar to examining data through the lens of fraud prevention, data trends may also show evidence of criminal behaviors like money laundering or even human trafficking. Join Kathryn O’Donnell, CEO and Founder of Clovis Technologies, and Navneet Mathur, Senior Director of Global Solutions at Neo4j, for this Graphs4Good webinar examining how graph database technology helps identify such activity and bring perpetrators to justice.
Graphdatenbanken eignen sich ideal, um sowohl einzelne Datensätze als auch die Zusammenhänge zwischen den Daten - Menschen, Dokumente, Maschinen etc. - zu visualisieren und stark vernetzte Informationen abzufragen. Auf diese Weise kann ein Kontext hergestellt und Verbindungen dargestellt werden. Knowledge Graph ist einer der wichtigsten Use Cases von Graphdatenbanken, denn sie eignen sich ideal, um sowohl einzelne Datensätze als auch die Zusammenhänge zwischen den Daten zu visualisieren und stark vernetzte Informationen abzufragen. Ausschließlich Graphen ermöglichen near real-time Abfragen über bisher isolierte Datensilos hinweg. Je mehr Daten miteinander verknüpft werden, desto mehr Kontext entsteht, den die Graph-Algorithmen abfragen und für Entscheidungen heranziehen können. Dr. Alexander Jarasch, Head of Data and Knowledge Management beim Deutschen Zentrum für Diabetesforschung (DZD) erläutert wie Graphdatenbanken in Kombination mit relationalen Datenbanken genutzt werden können. Ziel der übergeordneten Datenbank, DZDconnect, ist die Entstehung eines Informationskontextes, in dem Wissenschaftler gemeinsam forschen, ohne Tests wiederholen zu müssen. DZDconnect liegt als Layer über den relationalen Datenbanken, um bestehende Systeme und Datensilos im DZD zu verknüpfen. „Die Technologien erleichtern es, medizinische Fragen aus unterschiedlichen Blickwinkeln und indikationsübergreifend zu betrachten“, erklärt Dr. Alexander Jarasch. [DE]
Maximizing cost visibility is a common goal for large organizations, including the United States Department of Defense. The United States Army is required to track operating and support costs for weapon systems including weapons definition, force structure, inventory, requisitions, maintenance, ammunition and more. That equates to a vast amount of data and growing data management complexities. To address these challenges and achieve total cost visibility, the Army adopted the Neo4j graph database to create, manage, and analyze data relationships across the logistics community. In this webinar, Jason Zagalsky, Federal Account Manager at Neo4j, will provide a brief overview of Neo4j and Graphs In Government, followed by Preston Hendrickson, Principal Systems Analyst at CALIBRE Systems, describing how modernizing its cost tracking system gave the Army the cost visibility needed to meet DoD objectives.
Meta, a Chan Zuckerberg Science Initiative project, is designed to help users explore scientific research as it evolves in real-time. Using machine learning, Meta quickly analyzes, connects and organizes millions of scientific articles and preprints to build a live map of scientific developments. In this webinar, you’ll learn more about the knowledge graph powering Meta, and how this technology connects data for groundbreaking scientific research.
The graph database market is heating up and a wide variety of database and analytics vendors large and small are entering the space. Since not all graph databases are created equal, how do you know where to start when investigating a potential solution? While Gartner recently called out graph databases as a Top 10 Technology Trend for 2019, many organizations have never purchased one. Consequently, most people don’t understand what to look for, or what’s different about buying a graph database compared to traditional alternatives. In this session, we will ask a panel of experts to help identify the questions to ask when evaluating a graph database as well as the decisions you’ll need to make to ensure the right solution is purchased and implemented.
What’s the best way to understand your business challenge and accelerate innovation – Innovation Lab or Bootcamp? We would like to argue – it depends! The Innovation Lab is an onsite Design Sprint, where we educate business and technical users on the potential of graph technology and explore use cases by prototyping graph projects together with our customers. They gain a deep understanding of Graph Thinking and the possibilities in innovation and digital transformation within their organization. The Bootcamp is a more technical exercise where we educate the development team and co-create a small Proof of Concept based on a real-life dataset for a clearly identified use case. So, it depends on the customer’s specific needs and stage from what they benefit most – designing and prototyping versus creating.
Knowledge graphs are driving industry disruption and business transformation by bringing together previously disparate data, using connections for superior decision support, and adding context for more intelligent applications (including AI). In this session, we’ll walk through the fundamental elements of knowledge graphs including contextual relevance, dynamic self-updating, understandability with intelligent metadata, and the combination of heterogeneous data. Nav Mathur will discuss the 3 main types of knowledge graphs (context-rich search, external insights sensing, and enterprise NLP) that build on each other, and how and why real-world organizations are utilizing graphs as the building blocks for their applications. Also covered will be ideas on how to start building analytical applications on top of your knowledge graph using Neo4j Solution Frameworks quickly and easily.
t Neo4j we believe that “Graphs Are Everywhere”. In this session, we’ll be exploring graphs within the Retail industry. We’ll discuss a range of data that are commonly available within a retail organisation, both online and “brick and mortar". We’ll illustrate some graphs which can be created by linking together different elements of that data and discuss the retail use cases those graphs can enable and transform. We’ll specifically focus on use cases like Personalised Recommendations (with a live demo), Supply Chain Management, Logistics, and Customer 360. We'll also look at some relevant graph algorithms and talk about opportunities for integration with Artificial Intelligence/Machine Learning technologies, which can be used along with Neo4j to generate new value using retail data. eBay, Walmart, Wobi, and others already deploy Neo4j for use cases like price comparison or real-time contextual and learning recommendation engines.
Graph enhancements to AI and ML are changing the landscape of intelligent applications. In this webinar, we’ll focus on using graph feature engineering to improve the accuracy, precision, and recall of machine learning models. You’ll learn how graph algorithms can provide more predictive features as well as aid in feature selection to reduce overfitting. We’ll illustrate a link prediction workflow using Spark and Neo4j to predict collaboration and discuss our missteps and tips to get to measurable improvements.
Live interview from July 9th with Mark Grover, Product Manager at Lyft. Mark is working on Lyft's data discovery and metadata engine, Amundsen, which uses Neo4j as the backend data source for data discovery. During this 25-min session, Mark takes a deep dive into Amundsen's architecture which leverages a comprehensive Neo4j knowledge graph, centralized metadata and PageRank to achieve amazing results by reducing the time it takes to discover data by 10x! ### Blog post from Lyft describing the problem and solution (Amundsen): https://eng.lyft.com/amundsen-lyfts-data-discovery-metadata-engine-62d27254fbb9?gi=c1730f1508dd Open source code repo and documentation: https://github.com/lyft/amundsenfrontendlibrary
Graph technology is brilliant. In terms of graph theory, graphs are really well studied and have some amazing properties, especially for predictive analytics. But then there's AI: it's super-cool and also has some amazing abilities to guess the future given the past. So, which are we meant to choose? I'd argue we should use both. In this talk we'll see how graphs give us a framework for contextualizing the world around us. We'll explore how simple rules from graph theory can evolve our model to show how it might be in the future. But that's not all, we'll also see how we can take our graphs and feed them into our ML pipelines for better scores than simple row-wise data using graph neural nets. And we'll see how to learn on graphs directly with graph convolutional networks. Finally, we'll close the loop by asking our machine learning to tell us about other queries we should be running against the input graph to find patterns in data we don’t even know are valuable today. Watch this video on Neo4j.com here: https://go.neo4j.com/graphs-for-ai-guess-the-future-given-the-past-lp.html?ref=social-youtube For more webinars, check out the Neo4j Webinar library: https://neo4j.com/webinars/?ref=social-youtube #AI #MachineLearning #GraphDatabases
En esta webinar, nuestros destacados partners GraphEverywhere y Linkurious presentarán la base de datos Neo4j y la visualización de grafos de Linkurious junto con la perfecta integración de ambos. Además, también mostrarán casos de uso junto con una demo que integra a Neo4j con Linkurious. En resúmen, lo que aprenderás es: - Cómo los grafos pueden transformar/impactar tu negocio - Casos de uso - Beneficios de la implantación conjunta de las tecnologías de grafos y de visualización de grafos
As the graph industry has matured, many of Neo4j's customers are managing large-scale graph solution implementations. Every day the Neo4j Professional Services team helps customers make large and complex graph technology-based projects successful and deploy faster. In this webinar you will learn how the Neo4j Professional Services team is supporting customers. You will find out which activity suits your current project phase – from Innovation Lab or boot camp in the planning phase to pilots for testing and Managed Services for deploying and running graph databases.
With the introduction of the Neo4j Graph Platform and increased adoption of graph database technology across all industries, now is a better time than ever to get started with graphs. Join us for this introduction to Neo4j and graph databases. We'll discuss the primary use cases for graph databases and explore the properties of Neo4j that make those use cases possible.
In this session, we’ll be taking a look at graphs within the Manufacturing industry generally, and more specifically in the Automotive industry. We’ll review the types of data that are typically available within a manufacturing company, illustrate some graphs which can be created from that data, and discuss the use cases those graphs can enable and transform. The use cases presented will include Bills of Materials, Supply Chain Management, Logistics, and Claims Processing. We will also discuss where graph algorithms and integration with Artificial Intelligence/Machine Learning technologies can be used along with Neo4j to unlock new value from manufacturing data.
Neo4j Bloom is a graph visualization and exploration product. It offers a code-less search to graph insight experience suitable for end users of a graph-powered application. This enables graph novices and experts, technology and business side to easily collaborate and communicate. In addition, Bloom interprets and runs near natural language queries. Neo4j Bloom 1.1 is the next browser-based version of Bloom. Host it centrally on a server and allow access via a web browser, without the need for a desktop installation. With this update, Bloom makes it easy for project teams to collaborate and communicate using shared views of the same graph. What’s new in version 1.1: Enables Bloom for use by project teams Zero footprint access via modern HTML5 browsers - no local installation necessary Link Bloom to an external application and pass-in context for graph exploration Allow a graph admin to create separate perspectives for different user roles in the team
Graph enhancements to AI and ML are changing the landscape of intelligent applications. In this session, we’ll focus on how using connected features can help improve the accuracy, precision, and recall of machine learning models. You’ll learn how graph algorithms can provide more predictive features as well as aid in feature selection to reduce overfitting. We’ll look at a link prediction example to predict collaboration with measurable improvement when including graph-based features.