Graph algorithms such as PageRank, community detection and similarity matching have moved from the classroom to the data scientist's and business analyst's toolkit. Organizations are gaining actionable insights by connecting and analyzing their data.
Machine learning is an essential approach for getting the most insight out of your data. Machine learning enables data scientists and business users to scale their analysis and, when used in combination with graph algorithms, provides unprecedented insights that can have significant real-world impact.
In this latest Data Science Central webinar, we will:
Describe the five categories of graph algorithms: Shortest Path, Centrality, Community Detection, Similarity, and Classification;
Explain how graphs provide an intuitive data model to improve the accuracy of supervised machine learning with new training data & power explainable AI;
Examine how in-database machine learning such as deep learning, community detection, and low rank approximation is possible with scalable native graph databases;
Demonstrate how modern graph analytics tools can provide no-code data import, querying, feature extraction, and ML training.
We will cover use cases and case studies for graph analytics and machine learning that include real-time fraud detection at four of the top five global banks, personalized offers for 300 million consumers and care path recommendations to improve the well being of 50 million patients. We will also share open source community initiatives that are leveraging graph analytics to analyze COVID-19 data.
Dr. Victor Lee, Head of Product Strategy and Developer Relations - TigerGraph
Emma Liu, Senior Product Manager - TigerGraph
Stephanie Glen, Editorial Director - Data Science Central