- Releasing the 2.0 version of Graph Data Science Platform with tons of new features
- Bringing the power of Graph Data Science and Neo4j to the language you love with a native Python client
- Making it easier than ever to deploy with our new managed service AuraDS on Google Cloud
What Is Neo4j Graph Data Science?
If you’re new here… Neo4j Graph Data Science is a graph analytics and modeling platform. Using graph algorithms and machine learning (ML), data scientists identify patterns and behaviors to improve their models for use across recommendation engines, fraud detection, route optimization, and customer 360 scenarios.
What Are We Building?
We’re focused on building the most comprehensive graph data science solution on the market. To do that, we’re investing in five areas: ease of use, enterprise ready, graph built for data science, ecosystem integration, and cloud.
Talking about those investment areas helps organize the cool features we’re rolling out in our newest releases.
What’s New in Graph Data Science
Honestly, there’s so much in this release that it’s probably impossible to cover in a single blog post – and no one wants to read a novel. But some of the highlights include:
🤖 Machine Learning Pipelines just got a whole lot easier with the addition of a pipeline catalog; a new unified syntax for model configuration, training, and application; and support for random forest models.
🎓 Best in class data science with product tier graduation for Breadth First Search, Depth First Search, K-Nearest Neighbors, Delta Stepping, and the similarity functions. What this means for you is that these algorithms are all fully supported, parallelized, and optimized. Delta Stepping is 92 percent faster than our previous shortest path implementation!
🪄 New Enterprise features including cluster compatibility and graph backup/restore make it simple to go from proof of concept to production. You can now run graph data science workloads seamlessly alongside your transactional clusters, without worrying about losing your work.
🐍 Graph Data Science is part of your data science ecosystem with our new Python client. Data scientists don’t have to spend time learning Cypher or understanding transaction functions – now you can skip to the good part with our native Python API.
⛅ All of the insights, none of the hassle with AuraDS on Google Cloud Platform. With the launch of machine learning as a service platform, anyone can access Neo4j Graph Data Science, without the need for a team of software engineers, database admins, or IT approval. You can even pay with cloud credits!
Neo4j Graph Data Science as a Service with AuraDS
While cloud is one of our development pillars, it’s also a pretty freakin’ big deal for us (and you!). With AuraDS, you can use our fully hosted graph data science service to import, analyze, and visualize graph data through a SaaS license that includes all aspects of the infrastructure stack: storage (including backup storage), IO rate, data transfer, and more.
We’re available on Google Cloud Platform, so you can integrate with all of Google Cloud’s powerful ML services using VertexAI.
AuraDS includes Graph Data Science Enterprise Edition for data science graph algorithms and the modeling workspace and Bloom for visual data exploration, all supported by our graph database. Get started today!
Two years ago, Neo4j was the first Graph Data Science platform – and today, we’re releasing the best product on the market. From having the most algorithms and the easiest APIs to the simplest ways to get started, we’re pretty proud of the product we’ve built.
And it’s not just us – customers like VP of Engineering at OrbitMI, Slavisa Djokic agrees: “Without predictive modeling and graph analytics from Neo4j, we couldn’t have a product with this level of value. Neo4j Graph Data Science powers the engine for every routing decision that gets made for every one of our customers.”
Using Graph Data Science, OrbitMI built a maritime routing platform with sub-second response time, providing optimized routes saving time, money, and carbon emissions.