100 ML Innovation More Accuracy in Predictive Models Thanks to Graph Embeddings – NODES2022

Efficiency data scientists look for explainable, contextual, and accurate AI training and execution pipelines for industrial predictive models. Neo4j Graph Data Science enables the exploitation of relationships between data and the launch of workflows where graph algorithms compute new features that enrich predictive models and give new meaning to any data.

In this session, you’ll see a demonstration of this on the CORA dataset of scientific publications, well known in the data science ecosystem; Neo4j and graph embeddings increase several points of accuracy to predict the category of any given research paper.

Speakers: Nicolas Rouyer
Format: Lighting Talk 10-15 min, Full Session 30-45 min
Level: Advanced
Topics: #GraphDataScience, #Analytics, #MachineLearning, #General, #Advanced
Region: EMEA
Slides: https://dist.neo4j.com/nodes-20202-slides/100%20ML%20Innovation%20More%20Accuracy%20in%20Predictive%20Models%20Thanks%20to%20Graph%20Embeddings%20-%20NODES2022%20EMEA%20Advanced%208%20-%20Nicolas%20Rouyer.pdf

Visit https://neo4j.com/video/nodes-2022/ learn more at https://neo4j.com/developer/get-started and engage at https://community.neo4j.com