DataWhiz : An adaptive role-based AI analytics platform for dynamic dashboard generation and automated decision support
*Jeet J. DodiaCorresponding authorjeetdodia12@gmail.comDepartment of Computer Science & EngineeringInstitute of Computer TechnologyGanpat UniversityMehsana, Gujarat, 384012, India0009-0000-0253-1022View full profile → , Aniket Patelap02@ganpatuniversity.ac.inDepartment of Computer Science & EngineeringInstitute of Computer TechnologyGanpat UniversityMehsana, Gujarat, 384012, India0000-0001-7616-2610View full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Jul 2026
- Published Online:
- 30 Sep 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JSMS-1703
- Pages:
- 967–980
Abstract
Organizations rely on data-driven decision-making, yet conventional business intelligence platforms demand substantial manual preprocessing and analytical expertise. This paper presents DataWhiz, an adaptive role-based AI analytics platform that automatically transforms structured datasets into intelligent dashboards. Through semantic understanding, automated preprocessing, KPI recommendation, dynamic visualization, predictive modeling, and AI-assisted insight generation, the framework generates contextaware reports tailored to specific professional roles. Evaluated across four public datasets from diverse domains, DataWhiz significantly minimizes manual analytical effort while delivering precise decision support, effectively bridging the accessibility gap for both technical and non-technical enterprise users.
Keywords
Subject Classifications
References
[1] M. Alkayyal, S. Malberg, and G. Groh, “An LLM-based decision support system for strategic decision-making,” in Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track and Demo Track—ECML PKDD 2025, Lecture Notes in Computer Science, vol. 16022. Cham, Switzerland: Springer, pp. 460–464 (2025), doi: 10.1007/978-3-032-06129-4_31.
[2] K. K. L. Wong, L. Deng, Y. Liu, A. Li, and J. Tu, “Design and implementation of a local LLM-driven decision support system for AI-enhanced SCM,” J. Eng. Design, vol. 37, no. 6 (2026), doi: 10.1080/09544828.2025.2610791.
[3] C. Lawless, J. Schoeffer, L. Le, K. Rowan, S. Sen, C. St. Hill, J. Suh, and B. Sarrafzadeh, “‘I want it that way’: Enabling interactive decision support using LLM and constraint programming,” ACM Trans. Interact. Intell. Syst., vol. 14, no. 3, Art. no. 22 (2024), doi: 10.1145/3685053.
[4] C. Abdellaoui, S. Ferré, C. Boussadi, C. Burgun, and A. Delamarre, “Using large language models to automate the comparison and integration of evolving clinical practice guidelines into clinical decision support systems,” npj Digit. Med., vol. 9 (2026), doi: 10.1038/s41746-026-01726-4.
[5] P. N. Patil and P. S. Patil, “A LLM-based agent workflow for financial decision support using financial databases,” Saudi J. Econ. Manage. Res., vol. 10, no. 6, pp. 215–220 (2025), doi: 10.36348/sjemr.2025.v10i06.001.
[6] A. Jain, A. Mulay, D. Verma, A. Pandey, P. Ramu, and A. Garimella, “DECISIVE: Guiding user decisions with optimal preference elicitation from unstructured documents,” in Proc. 64th Annu. Meeting Assoc. Comput. Linguistics (ACL), vol. 1, pp. 31774–31786 (2026), doi: 10.18653/v1/2026.acl-long.1465.
[7] S. M. F. Tauhid, S. Tanweer, Md. T. Nafis, M. A. Ahad, and S. M. F. Malik, “Machine learning-driven data analytics for improved diagnostic accuracy, treatment efficacy, and real-time monitoring in smart health care,” J. Inf. Optim. Sci., vol. 46, no. 7, pp. 2291–2317 (2025), doi: 10.47974/JIOS-2031.
[8] A. Chauhan, S. Kumar, A. Kumar Karn, and S. Sharma, “Role of artificial intelligence in optimizing digital marketing—an empirical study,” J. Inf. Optim. Sci., vol. 46, no. 2, pp. 439–451 (2025), doi: 10.47974/JIOS-1926.
