GraphBI: Expanding Analytics to All Data with GenAI, Graph, and Visual Analytics

Session Track: AI Engineering

Session Time: 09:30 pm - 10:00 pm November 6

Session description

Current BI systems focus on structured data, representing only 20% of organizational information, leaving 80% of unstructured data unused. This presentation introduces GraphBI, a solution that leverages generative AI, graph technology, and interactive visual analytics to fully utilize enterprise data. Using LLMs to process unstructured data into a knowledge representation format is central to building a robust and scalable solution. However traditional knowledge graphs often over-abstract, omitting vital nuances. This presentation proposes a refined approach, "Knowledge Map," to preserve crucial details. By integrating Knowledge Map into a well-developed analytical workflow with Neo4j as the graph data management layer, GraphBI ensures a transparent and granular step-by-step analytical process that is comprehensive, reliable, and precise. We will walk through the GraphBI workflow with use cases, exploring best practices and challenges in each step of the process—managing both structured and unstructured data, data pre-processing with GenAI, iterative analytics using a BI-focused graph grammar, and final insight presentation. This approach uniquely surfaces business insights by effectively incorporating all types of data.