"NIEMOpen for Information Exchange: complex system modeling with knowledge graphs"
with guest Bradley Bolliger from EY
Tue Oct 28, 09:00-10:00 US Pacific
https://watch.getcontrast.io/register/senzing-gphv2e2
π§ Tune in to see how machine-to-machine clarity helps return complex systems to human scale.
#Senzing #ERKG #NIEMOpen
I really enjoyed the 6th Annual MLOps World | GenAI Summit in Austin, Texas this week, and am grateful to get to meet and talk with many amazing people in the field, and also get to present about Senzing and where entity resolution, graph technologies, and context engineering meet to address enormous challenges in anti-fraud.
Many thanks to David Scharbach and crew for producing this outstanding event!
Here's a link to my full slide deck: https://derwen.ai/s/khj9#0
The next four weeks will be busy with conferences! Got loads of new Senzing material to show, including some libraries and tutorials which may be quite helpful. Check these highly recommended events:
* Oct 01 Semantic Layer Symposium @ Copenhagen https://semanticlayersymposium.com/
* Oct 02 Senzing Summit
* Oct 08-09 MLOps World Summit @ Austin https://mlopsworld.com/
* Oct 28-30 ODSC West @ SFO https://odsc.com/california/
A new `sz_semantics` library is available in the "Senzing Garage" on GitHub and released as a package on PyPi:
* https://github.com/senzing-garage/sz-semantics
* https://pypi.org/project/sz_semantics/
π§ Next up on "Graph Power Hour!"
GraphRAG at scale with Amazon Neptune and Amazon Bedrock
Tue July 15
09:00-10:00 US Pacific
https://app.getcontrast.io/register/senzing-gphv1e8?utm_campaign=ERKG&utm_content=337763674&utm_medium=social&utm_source=linkedin&hss_channel=lcp-18283464
I'm thrilled to be talking with Ozan Eken and Nicole Moldovan from Amazon Neptune to discuss in depth about new GraphRAG capabilities.
Given the recent GA release, cloud-based applications can build graph vector stores directly from Amazon Bedrock for use with Neptune GraphRAG.
"Knowledge Graph Development for More Effective AI Systems: Systematic Approaches"
Tue Apr 15, 09:00 US pacific
https://bit.ly/GraphPowerHour1e5li
Join us for a presentation by Mike Dillinger, with discussion between Mike and host Paco Nathan, plus live Q&A with the audience.
Let's talk about relationships, arguably the most important aspect of building knowledge graphs, albeit too often overlooked.
Check this EY whitepaper from Subhankar Sarkar and Paul Wormeli about entity resolution + knowledge graphs for justice systems modernization:
https://www.ey.com/en_us/insights/government-public-sector/justice-information-systems-modernization-reimagined
> At EY we're reimagining collaboration among state and local justice departments to create a seamless ecosystem.
Looking forward to:
"Catching Bad Guys: leveraging entity resolution to construct graphs for anti-fraud"
Estes Park, by Semantic Arts
Feb 6, 10:00-11:00 US Pacific
https://www.linkedin.com/events/7288252493568860161/comments/
Join us for a Semantic Arts, Inc. Estes Park Group community webinar featuring Paco Nathan, Principal Developer Relations Engineer at Senzing. Paco will discuss how to leverage entity resolution to construct knowledge graphs for anti-fraud applications. The event will be co-hosted by Steve Case and Joaquin Melara. ESTES PARK GROUP: Semantic Arts, Inc.'s Estes Park Group, is a non-salesy monthly virtual community gathering where guest speakers are invited to share lessons learned from their work developing data-centric architectures. ABOUT THE SESSION: "Catching Bad Guys: Leveraging Entity Resolution to Construct Graphs for Anti-Fraud" will demonstrate how to use graph technology to identify key players in financial fraud. This session will use open datasets and an anti-fraud data model to illustrate how entity resolution merges data, creates entities and relations, and constructs a knowledge graph. You'll learn how this approach enhances data quality and supports trustworthy AI applications, while also enabling evidence-based decision-making and auditing. We'll explore design patterns for integrating an entity resolution service into data engineering practices and recommend community resources for further learning about investigative graphs and open data practices.
Really looking forward to PyData Global 2024 (online) !!
I'll be presenting
"Catching Bad Guys using open data and open models for graphs"
Thu Dec 5, 14:30-15:00 BST
https://global2024.pydata.org/cfp/talk/XMU9X9/
#PyDataGlobal #Senzing #ERKG #knowledgegraphs #AI #darkmoney #AML #entityresolution #opendata
Entity resolution (ER) is a complex process focused on data quality, used for constructing and updating knowledge graphs (KGs). GraphRAG is a popular way to use KGs to ground AI apps. Most GraphRAG tutorials use LLMs to build graph automatically from unstructured data. However, what if you're working on use cases such as investigative journalism and sanctions compliance -- "catching bad guys" -- where transparency for decisions and evidence are required? This talk shows how to construct an investigative graph about potential money laundering, using ER to merge open data from ICIJ Offshore Leaks, Open Ownership, and OpenSanctions. First we'll build a "backbone" for the graph in ways which preserve evidence and allow for audits. Next we'll use spaCy pipelines to parse related news articles, using `GLiNER` to extract entities, then the new `spacy-lancedb-linker` to link them into the graph. Finally, we'll show graph analytics that make use of the results -- tying into what's needed for use cases such as GraphRAG. This approach uses Python open source libraries, e.g., the `KΓΉzuDB` graph database and `LanceDB` vector database. For each NLP task we use state-of-the-art open models (mostly not LLMs) emphasizing how to tune for a domain context: _named entity recognition_, _relation extraction_, _textgraph_, and _entity linking_. Overall, we show how to leverage open data, open models, and open source to build investigative graphs which are accountable, exploring otherwise hidden relations in the data that indicate fraud or corruption. This illustrates techniques in production use cases for anti-money laundering (AML), ultimate beneficial owner (UBO), rapid movement of funds (RMF), and other areas of sanctions compliance in general. All of the code is provided on GitHub, organized in Jupyter notebooks.
Paco Xander Nathan
paco xander nathan
