Neo4j Graph Data Science
Although Neo4j has traditionally been used for transaction workloads, in recent years it is increasingly being used at the heart of graph analytics platforms. This guide introduces the tools available for applying graph analytics to your connected data.
Graph Data Science is a science-driven approach to gain knowledge from the relationships and structures in data, typically to power predictions. It describes a toolbox of techniques that help data scientists answer questions and explain outcomes using graph data.
Graph Data Science techniques can be used as part of a variety of different applications and use cases.
Graph queries support domain experts by answering common questions.
Graph algorithms help make sense of the global structure of a graph, and the results used for standalone analysis or as features in a machine learning model.
Graph embeddings are a core component of similarity graphs that power recommendation systems.
Natural Language Processing techniques support content based filtering recommendations and knowledge graph completion.
The Neo4j Graph Data Science Library (GDSL) provides efficiently implemented, parallel versions of common graph algorithms for Neo4j 3.x and Neo4j 4.x exposed as Cypher procedures.
The library contains implementations of classic graph algorithms in the path finding, centrality, and community detection categories. It also includes algorithms that are well suited for data science problems, like link prediction and weighted and unweighted similarity.
Neo4j offers powerful querying capabilities for structured data, but a lot of the world’s data exists in text documents. NLP techniques can help to extract the latent structure in these documents.
Was this page helpful?