
Research Article
Insight Pro: Leveraging Generative AI for Natural Language to SQL Conversion in Business Analytics
@INPROCEEDINGS{10.4108/eai.28-4-2025.2358008, author={Abinesh P and Hari Sankar J and Keerthana S and Narayanan C P and Naresh K and Sunanda Christy Kumari A}, title={Insight Pro: Leveraging Generative AI for Natural Language to SQL Conversion in Business Analytics}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={natural language to sql conversational query systems business intelligence google gemini api query accuracy data accessibility visualization integration user experience}, doi={10.4108/eai.28-4-2025.2358008} }
- Abinesh P
Hari Sankar J
Keerthana S
Narayanan C P
Naresh K
Sunanda Christy Kumari A
Year: 2025
Insight Pro: Leveraging Generative AI for Natural Language to SQL Conversion in Business Analytics
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2358008
Abstract
The study investigates the growing need for easy to use business analytics tools and (user) friendly data interaction software, concentrating on the adoption behavior of natural language query for SQL generation platforms. Indeed, the increasing pervasiveness of AI-based technologies and the rising level of digital literacy at the workplace are changing users' access to and utilization of organizational data by offering them simplified, conversation-based query toolkits. The experimental results show that although up to date, the proposed kind of platforms are so prevailing in various fields, but they still suffer from some issues like wrong query accuracy, lack of generalization to new domains and also sometimes delay. By utilizing Insight Pro, an application that works beneath the Google Gemini Pro API, we provide structured assessment on four categories of topics: precision of query, context accuracy, response time, and ease of use with the interface. It also investigates how contextual factors, such as business domain complexity, data literacy, or systems integration, affect user engagement. Data for the study was gathered by using a formal testing process with 100 subjects from diverse organizations, covering a wide range of performance obstacles and user expectations.