Modern machine learning demands new approaches. A powerful ML workflow requires more than picking the right algorithms. You also need the right tools, technology, datasets and model to brew your secret ingredient: context.
In his book, Graph-Powered Machine Learning, Dr. Alessandro Negro explores the new way of applying graph-powered machine learning to recommendation engines, fraud detection systems, natural language processing. By making connections explicit, graphs harness the power of context to help you build more accurate, real-time machine learning models.
In this interview with the book’s author, you’ll learn more about:
- The role of graph technology in machine learning applications.
- How graphs provide better context to improve your ML understanding and workflow.
- How graph data science enhances four of the most common recommendation techniques: content-based, collaborative filtering, session-based, and context-aware recommendations.
- Data modeling considerations for graph-based recommendation engines.
- How to approach designing a hybrid recommendation engine that incorporates multiple approaches.
Weidong Yang is the founder and CEO of Kineviz. He holds a doctorate in Physics and a Master's degree in Computer and Information Science. Prior to founding Kineviz, he worked for ten years as a product manager and R&D scientist in the Semiconductor industry. He has been awarded 11 US patents and contributed to 20+ peer-review publications.
Axel Morgner founded the open source project "Structr" and a co-founder and managing director of Structr GmbH, the company behind the project. Structr is a low-code development environment that makes intensive use of graph technology. Axel Morgner is a graduate physicist, works and lives in Frankfurt, Germany and has worked as a developer, architect and project manager at Oracle, among others, before founding various companies.
Dr. Martin Preusse has a background in biochemistry and a PhD in computational biology. With his Neo4j consultancy Kaiser & Preusse, he builds knowledge graph applications for medical research, biotech and pharma. His main interests are data modeling and new concepts to solve real-world business problems with knowledge graphs. He is based in beautiful Freiburg in the south-west of Germany, close to France and Switzerland.
Lance Walter has more than two decades of enterprise product management and marketing experience.
Lance started his career in technical roles at Oracle supporting enterprise relational database deployments. Since then, Lance has worked at industry leaders like Siebel Systems and Business Objects, as well as successful startups including Onlink (acquired by Siebel Systems), Pentaho (acquired by Hitachi Data Systems), Aria Systems and Capriza. Lance’s first experience with alternative database platforms was at Arbor Software, the pioneer of the multi-dimensional database / OLAP market.