With the aim to monitor, prevent, and predict cyber attacks on various systems and infrastructures, the cyber defence company needed a solution to ingest and connect all available data and discover threat patterns.
In association with The Times, Raconteur published the Fraud & Financial Crime 2023 report.
"Economic downturns have a habit of becoming a breeding ground for fraud. And with social media, cryptocurrencies and non-financial sectors such as property, fine art and jewellery also proving hotspots for financial crime, there are plenty of dangers to watch out for. Will regulators be able to keep up in this constantly evolving landscape?"
In the realm of intelligence analysis, data often needs to be contextualised within geographic or temporal frameworks. Through Geospatial Analysis, Hume provides visibility into the locations of the data, while Temporal Analysis allows for a deeper understanding of the data's evolution over time.
This video will demonstrate how Hume's Temporal and Geospatial Analysis features revolutionise police investigations. By leveraging Hume's powerful graph analytics engine, investigators are able to quickly analyse temporal and geospatial data, providing valuable insights into suspects and their co-defendants. This allows police to uncover the timeline and locations of criminal activity, such as the positioning of a cell phone or a vehicle and its changes over time, which can lead to the identification of a primary suspect and their possible accomplices.
The Temporal and Geospatial Analysis capabilities of Hume provide invaluable context, allowing for more intuitive analysis than would otherwise be possible.
*The data used in the video are entirely fictitious.
Hume is lauded for its ability to customise the system's features and tasks, giving analysts the power to tailor it to their individual needs. Its impressive internal creative capabilities, in combination with features such as Styling, Grouping and Computed Attributes, allow users to maintain full control over the system.
In this video, we will demonstrate how Hume enables effective navigation of a knowledge graph with its Styling features. During a data analysis session, it is paramount to be able to differentiate between various entities and relationships. Hume allows users to customise, style, and display the nodes and relationships on the canvas according to the requirements of the investigation.
The features of Hume offer almost limitless flexibility and styling options for graph visualisations, allowing end-users to quickly traverse their graphs. Check our website to learn more about the features that will bolster intelligence analysis.
*The data used in the video are entirely fictitious.
The emergence or disappearance of patterns in your data can be a mission-critical moment. That's why Hume provides continuous monitoring of patterns of interest, ensuring that stakeholders never miss an important update.
This video will showcase how effortless it is to use the Alerting feature in Hume and receive instant notifications of any changes in your data. When conducting an investigation, it is likely that you will want to keep track of specific interactions made by a person of interest, such as their communication and calls, or their presence in a specific location.
The Hume graph analytics solution's Alerting feature will ensure that you are kept abreast of customisable patterns. This can all be done without the need for coding, thanks to the Advanced Expand feature.
Read more about the benefits of automated Alerting and stay on top of emerging trends and patterns of intelligence analysis.
*The data used in the video are entirely fictitious.
Traversing a graph database has never been easier than with Hume! With just a few clicks, you can effortlessly navigate through your knowledge graph, no GQL Cypher writing required. Hume makes graph database traversal simple and effective.
This video will demonstrate how Hume's Advanced Expand feature makes it straightforward to explore data and uncover insights without requiring any coding knowledge. Even those without experience in Neo4j's graph query language, Cypher, can benefit from Hume's low technical requirements.
Advanced Expand is a useful feature of Hume, a no-code query builder that allows analysts to easily access and connect pertinent data. For example, the video demonstrates how it can be used to swiftly connect witness statements in a murder investigation, thereby aiding in the identification of a primary suspect.
*The data used in the video are entirely fictitious.
Run complex intelligence analysis with ease using Hume Actions - customised queries that offer the full power of Neo4j's Cypher query language. With a single click, unlock answers to investigative questions and unlock the power of your data.
In this video, we will explore how Hume Actions can help you answer these questions and more. With Hume Actions, you can quickly and easily query your data to gain insights into a person of interest's connections, affiliations, and activities. This feature allows you to quickly pull up profiles and data associated with a particular person, allowing you to gain a better understanding of the person's criminal background and potential connections. Hume Actions also helps you to keep track of your investigations and can even alert you when new information becomes available. With Hume Actions, you can quickly gain a better understanding of criminal activity and get closer to solving your case.
The Actions feature in Hume makes it easier for analysts to answer important questions quickly. Learn more about the powerful Hume features that enable fast and accurate analysis.
*The data used in the video are entirely fictitious.
Fabio Montagna is Lead Machine Learning Engineer at GraphAware and presented Temporal Graph Analysis at NODES2022. In this session, we’ll share our experience with horizon scanning over a graph of medical research papers. By leveraging the author keywords from scientific publications, it’s possible to build a cooccurrence graph with a temporal component provided by the paper publication date. We’ll show how we can analyze trends and evolution patterns using an unsupervised algorithm that assigns roles to author keyword.
Christophe Willemsen, CTO at GraphAware, spoke on NODES2022 about using Neo4j with Docker and Docker Compose, presented tips and tricks on basic usage, gave an explanation of the Docker image itself, backups and restore and building custom images extending the official Neo4j image.
Federica Ventruto and Alessia Melania Lonoce are Junior Data Scientists at GraphAware who spoke at NODES2022. Natural language processing is an indispensable toolkit to build knowledge graphs from unstructured data. However, it comes with a price. Keywords and entities in unstructured texts are ambiguous - the same concept can be expressed by many different linguistic variations. The resulting knowledge graph would thus be polluted with many nodes representing the same entity without any order. In this session, we show how the semantic similarity based on transformer embeddings and agglomerative clustering can help in the domain of academic disciplines and research fields and how Neo4j improves the browsing experience of this knowledge graph.
Vlasta Kůs is Lead Data Scientist at GraphAware and presented at NODES2022. Public archives contain incredible amount of knowledge. In this session, we’ll cover a real use case of building a knowledge graph for the archive of a major foundation to help empower researchers (or business analysts) to access previously unavailable levels of insights. This archive, going up to a century back, contains detailed information about funded projects and conversations preceding them, budgets, research endeavors, and outcomes, as well as priceless knowledge about influence networks of foundation representatives, researchers, and students. A particular challenge was that the same events were described in multiple sources. The only way to leverage all of this knowledge was through the use of advanced analytics and machine learning. We will explore the technologies (including OCR, NLP, and graph data science) and complex pipelines employed to create this major knowledge graph.
