Zach Blumenfeld is a graph enthusiast who helps data scientists, engineers, and business leaders understand and implement Graph Analytics to solve challenging business problems.
He has firsthand experience with a wide range of modern day analytical challenges, including criminal fraud detection, identity resolution, and recommendation systems. Serving in both data science and software developer capacities, Zach has applied graph computing for law enforcement and government entities in support of missions that counter drug trafficking, human smuggling, money laundering, and child exploitation. He has led the development and deployment of full stack graph systems designed to facilitate broad search and analytical query requirements.
Zach is excited to join Neo4j as Data Science Product Specialist, where he will help empower the field with Neo4j’s industry leading Graph Data Science (GDS) capabilities.
Using Neo4j Graph Data Science to Understand and Improve Your Supply Chain Performance In this post we demonstrate how Neo4j Graph Data Science can be applied to supply chain data to: Find new, faster, paths through supply chain processes with potential to improve performance by up to... read more
In part 1 of this series, we demonstrated how supply chain data can be modeled into a graph, imported into Neo4j, and analyzed using Graph Data Science (GDS). We walked through how to visualize the supply chain in Bloom and used the new GDS integration to understand operational load, flow... read more
Actionable insights in minutes, using Neo4j Graph Data Science and Bloom to intuitively visualize and extract supply chain insights around operational load, flow control, and regional patterns. Supply chains are inherently complex, involving multiple stages, inputs, outputs, and... read more
In the three previous parts of this series, we explored the graph, identified new fraud risk accounts and communities, and covered techniques to recommend new suspicious users. In this section, we will cover how to apply graph machine learning to predict the high fraud risk user accounts we labeled... read more
In parts 1 & 2 of this series, we explored the graph and identified high risk fraud communities. At this stage, we may want to expand beyond our business logic to automatically identify other users that are suspiciously similar to the fraud risks already identified. Neo4j and GDS makes it... read more
Identifying communities that reflect underlying groups of individuals is often a key step to fraud detection. In part 1 of this series, we explored with Louvain. In part 2, we will provide more formal definitions for resolving entities that will allow us to partition well-defined communities in a... read more
In the first part of this fraud detection series, we will introduce the sample graph dataset we are using and begin exploring the graph for potential fraud patterns.The technical resources to reproduce this analysis and the analysis in all subsequent parts of this series are contained in this... read more
Fraud Detection is one of today’s most challenging data science problems. Thankfully, Neo4j Graph Data Science (GDS) offers practical solutions that empower data scientists to make rapid progress in fraud detection analytics and machine learning. SummaryWhether you are responsible for... read more
In this post we explore how to get started with practical and scalable recommendation in graph. We will walk through a fundamental example with news recommendation on a dataset containing 17.5 million click events and around 750K users. We will leverage Neo4j and the Graph Data Science... read more
Photo by Alina Grubnyak on UnsplashWhile Supervised Entity Resolution (ER) can be immensely valuable, it is sometimes difficult to apply and scale in the real-world enterprise setting.In this post, I explore how the Neo4j Graph Data Science (GDS) library can be applied to rapidly develop... read more