AI-Driven Adaptive Indexing and Query Optimization in Graph Databases
- Version
- Download 19
- File Size 748.91 KB
- File Count 1
- Create Date 28 May 2025
- Last Updated 28 May 2025
AI-Driven Adaptive Indexing and Query Optimization in Graph Databases
Authors:
Mrinal Deb1, Nimit Garg2, Karunya Sehgal3, R. K. Yadav4*
1*Department of Computer Sc. Engineering, Delhi Technological University, New Delhi.
*Corresponding author(s). E-mail(s): rkyadav@dtu.ac.in; Contributing authors: mrinalenquiry@gmail.com; nimitgarg8@gmail.com; karunyasehgal@gmail.com;
Abstract: Graph databases have emerged as a pivotal solution for managing intercon- nected data, providing a more intuitive way to model relationships compared to traditional relational databases. As the complexity and scale of the graph data increase, the need for efficient indexing and intelligent query optimization becomes paramount. This paper presents an AI-driven approach to adaptive indexing and query optimization in Neo4j, leveraging a movie dataset. By inte- grating Python-based preprocessing and fine-tuning an OpenAI language model on a custom schema, we demonstrate how natural language queries can be opti- mized into efficient Cypher queries. Our study covers the performance of simple, complex, recursive, and subquery-based queries and evaluates the effectiveness of AI-generated optimizations.
Keywords: Graph Databases, Query Optimization, AI Driven Indexing
Download