A Multi-Agent Generative AI–Driven Framework for the Rapid Validation of Digital Business Models through Synthetic Market Intelligence

Sabar Aritonang Rajagukguk

doi:10.48084/etasr.16536

Authors

Sabar Aritonang Rajagukguk Management Department, Binus Online Learning, Bina Nusantara University, Jakarta, Indonesia

Volume: 16 | Issue: 3 | Pages: 35199-35204 | June 2026 | https://doi.org/10.48084/etasr.16536

Received: 27 November 2025 | Revised: 19 December 2025, 1 February 2026, 15 February 2026, and 18 February 2026 | Accepted: 19 February 2026 | Online: 6 June 2026

Corresponding author: Sabar Aritonang Rajagukguk

Abstract

Digital business transformation requires rapid mechanisms to validate new business models, while traditional market research remains slow, costly, and constrained by privacy limitations. This study presents the Synthetic Market Intelligence Framework (SMIF), a multi-agent generative AI system that constructs synthetic market environments to accelerate validation. SMIF employs specialized agents to simulate customer personas, competitor responses, and market dynamics within a coordinated orchestration workflow. Across 150 business cases and a comparative evaluation against traditional validation methods, SMIF achieved a correlation of 0.893 with observed market outcomes and reduced validation time and cost by 94% and 87%, respectively. The framework incorporates grounding and constraint mechanisms to reduce hallucination risk and supports scalability through bounded context management. The results indicate that synthetic validation environments can increase iteration speed and improve decision support in the evaluated settings.

Keywords:

synthetic market simulation, multi-agent generative AI architecture, accelerated business model testing, digital transformation enablement, generative AI-driven strategy, enterprise market intelligence systems, data-informed strategic decision processes, innovation modeling and evaluation

References

S. Bresciani, K. H. Huarng, A. Malhotra, and A. Ferraris, "Digital transformation as a springboard for product, process and business model innovation," Journal of Business Research, vol. 128, pp. 204–210, May 2021.

Z. Mayhook, "Using keyword analysis for market validation research," Journal of Business & Finance Librarianship, vol. 30, no. 1, pp. 1–17, Jan. 2025.

O. Fagbohun et al., "GreenIQ: A Deep Search Platform for Comprehensive Carbon Market Analysis and Automated Report Generation." arXiv, Mar. 21, 2025.

A. Kallmuenzer, A. Mikhaylov, M. Chelaru, and W. Czakon, "Adoption and performance outcome of digitalization in small and medium-sized enterprises," Review of Managerial Science, vol. 19, no. 7, pp. 2011–2038, July 2025.

K. H. Huarng and A. Rey-Martí, "Special issue on digital transformations and value creation in management," European Journal of Management and Business Economics, vol. 28, no. 2, pp. 110–113, July 2019.

S. Oludapo, N. Carroll, and M. Helfert, "Why do so many digital transformations fail? A bibliometric analysis and future research agenda," Journal of Business Research, vol. 174, Mar. 2024, Art. no. 114528.

A. Akkiraju, "Synthetic Data Generation: Revolutionizing Ai Development And Privacy," International Journal Of Computer Engineering And Technology, vol. 16, no. 1, pp. 3623–3637, Feb. 2025.

S. Kapania, S. Ballard, A. Kessler, and J. W. Vaughan, "Examining the Expanding Role of Synthetic Data Throughout the AI Development Pipeline." arXiv, 2025.

C. Zhang, "Dynamic Asset Pricing: Integrating FinBERT-Based Sentiment Quantification with the Fama--French Five-Factor Model." arXiv, 2025.

N. Sassi, K. Ghesira, and K. B. Salah, "Using Multi-agent System to Solve Distributed Constraint Optimization Problems," in 2014 2nd International Symposium on Computational and Business Intelligence, Dec. 2014, pp. 30–34.

N. E. A. Amrani, O. E. K. Abra, M. Youssfi, and O. Bouattane, "A Novel Deep Learning Approach for Semantic Interoperability Between Heteregeneous Multi-Agent Systems," Engineering, Technology & Applied Science Research, vol. 9, no. 4, pp. 4566–4573, Aug. 2019.

M. Geissdoerfer, P. Savaget, N. Bocken, and E. J. Hultink, "Prototyping, experimentation, and piloting in the business model context," Industrial Marketing Management, vol. 102, pp. 564–575, Apr. 2022.

M. S. E. Namaki, "Could Synthetic Data Influence Strategic Thinking?," Scholedge International Journal of Business Policy, vol. 10, no. 8, Jan. 2025, Art. no. 80.

K. Al-Mutawah, "A study of corporate culture compatibility on supply chain performance," Ph.D. dissertation, Monash University, Australia, 2017.

S. A. Rajagukguk, "Synthetic Market Intelligence Dataset." Zenodo, Aug. 04, 2025.

S. Wang and H. Zhang, "Enhancing cross-border shopping through AI chatbots: an antecedents–engagement–consequences perspective of brand-consumer interactions," Journal of Product & Brand Management, vol. 35, no. 4, pp. 615–629, Mar. 2026.

S. Wang and H. Zhang, "Inter-organizational cooperation in digital green supply chains: A catalyst for eco-innovations and sustainable business practices," Journal of Cleaner Production, vol. 472, Sept. 2024, Art. no. 143383.

S. Wang and H. Zhang, "Enhancing environmental, social, and governance performance through artificial intelligence supply chains in the energy industry: Roles of innovation, collaboration, and proactive sustainability strategy," Renewable Energy, vol. 245, June 2025, Art. no. 122855.