August 2023 Summaries

Fraud detection is crucial in various industries, and as the world becomes increasingly digital, businesses must adapt their strategies to combat fraudulent activities effectively. Graph machine learning techniques can improve fraud detection by up to 20% in the Ethereum blockchain. By utilizing graph data structures, relationships between entities can be represented more naturally, allowing for richer feature extraction and improved similarity determination. Incorporating graph features into traditional ML models or using native graph models like Graph Neural Networks (GNNs) can lead to significant accuracy improvements in fraud detection tasks. TigerGraph is a highly scalable and performant graph database that enables businesses to compute novel graph features, making it an ideal choice for implementing these techniques.

Large Language Models (LLMs) have proven their usefulness in general-purpose information retrieval, but businesses often struggle with how to ask questions about their specific data using these models. Since LLMs are neural networks with fixed-size inputs, they can only process a limited amount of data at once, known as context length or tokens. To overcome this limitation and enable LLMs to reason with sensitive data that cannot be incorporated into training datasets, highly scalable, deduplicated, and relationship-rich external data sources like graph databases are needed. TigerGraph is one such solution that allows for the execution of scalable graph algorithms and can integrate with LangChain, a Python library that integrates LLMs with various data sources. By building LangChain tools to interact with TigerGraph, developers can reduce hallucinations in model responses and enable them to answer questions whose answers were not present in their training datasets. This integration opens the door for business analysts to be more productive and have richer information at their fingertips.

Graph data and graph analytics are becoming increasingly important in businesses as they help to improve analytics, cut losses, and find more revenue. Graph databases allow for faster and more accurate analysis of interdependencies and interrelations compared to other types of databases. Key use cases include financial crime detection, customer 360 with entity resolution, personalized recommendations, and modeling and optimization of operational systems and networks. The book "Graph-Powered Analytics and Machine Learning with TigerGraph" aims to address the needs of readers with varying technical backgrounds and learning styles by presenting material in concept chapters and hands-on use case example chapters. It also demonstrates using TigerGraph, a scalable and fast platform for graph analytics, along with its GSQL query language and GraphStudio Starter Kits.