OPTIC—OPtimized Translation and Interaction for Cloud-Costs: Use of FOCUS Standardization and LLM Integration for Cloud Billing Analysis
Year: 2025
Type: article
Abstract: Managing billing data across multicloud environments remains a significant challenge due to heterogeneous data formats, fragmented cost metrics, and the technical complexity of cost analysis. This paper introduces the OPtimized Translation & Interaction for Cloud-costs (OPTIC) framework, a novel approach that combines the FinOps Open Cost and Usage Specification (FOCUS) with Large Language Models (LLMs) to enable natural language interaction with standardized billing data. OPTIC automates the Extraction, Transformation, and Loading (ETL) of cost and usage data from major cloud providers, consolidates them into a unified SQL database, and translates natural user questions into SQL queries using LLM-based text-to-SQL techniques. A web-based interface supports both predefined dashboards and a chatbot for dynamic queries. Experimental results using benchmark datasets demonstrate an accuracy of up to 82.5% in SQL generation, showcasing the framework’s effectiveness in Financial Operations (FinOps) contexts. By simplifying multicloud cost analysis, OPTIC aims to democratize access to financial insights and support data-driven decision-making in both technical and non-technical teams.
Source: IEEE Access
Authors: Gilberto N. Junior, César Marcon
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W4417284375