Automatic Data Transformation Using Large Language Model - An Experimental Study on Building Energy Data

Ankita Sharma, Xuanmao Li, Hong Guan, Guoxin Sun, Liang Zhang, Lanjun Wang, Kesheng Wu, Lei Cao, Erkang Zhu, Alexander Sim, Teresa Wu, Jia Zou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Existing approaches to automatic data transformation are insufficient to meet the requirements in many real-world scenarios, such as the building sector. First, there is no convenient interface for domain experts to provide domain knowledge easily. Second, they require significant training data collection overheads. Third, the accuracy suffers from complicated schema changes. To address these shortcomings, we present a novel approach that leverages the unique capabilities of large language models (LLMs) in coding, complex reasoning, and zero-shot learning to generate SQL code that transforms the source datasets into the target datasets. We demonstrate the viability of this approach by designing an LLM-based framework, termed SQLMorpher, which comprises a prompt generator that integrates the initial prompt with optional domain knowledge and historical patterns in external databases. It also implements an iterative prompt optimization mechanism that automatically improves the prompt based on flaw detection. The key contributions of this work include (1) pioneering an end-to-end LLM-based solution for data transformation, (2) developing a benchmark dataset of 105 real-world building energy data transformation problems, and (3) conducting an extensive empirical evaluation where our approach achieved 96% accuracy in all 105 problems. SQLMorpher demonstrates the effectiveness of utilizing LLMs in complex, domain-specific challenges, highlighting the potential of their potential to drive sustainable solutions.

Original languageEnglish (US)
Title of host publicationProceedings - 2023 IEEE International Conference on Big Data, BigData 2023
EditorsJingrui He, Themis Palpanas, Xiaohua Hu, Alfredo Cuzzocrea, Dejing Dou, Dominik Slezak, Wei Wang, Aleksandra Gruca, Jerry Chun-Wei Lin, Rakesh Agrawal
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1824-1834
Number of pages11
ISBN (Electronic)9798350324457
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Big Data, BigData 2023 -
Duration: Jan 1 2023 → …

Publication series

NameProceedings - 2023 IEEE International Conference on Big Data, BigData 2023

Conference

Conference2023 IEEE International Conference on Big Data, BigData 2023
Period1/1/23 → …

Keywords

  • ChatGPT
  • data transformation
  • large language model
  • smart building
  • Text2SQL

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Automatic Data Transformation Using Large Language Model - An Experimental Study on Building Energy Data'. Together they form a unique fingerprint.

Cite this