AI-Driven Decision Intelligence Architecture for Strategic Optimization of Grant Funding Outcomes in Mission-Driven Organizations: A Decision Science Perspective
DOI:
https://doi.org/10.55578/jdso.2602.003Keywords:
Decision Intelligence, Grant Portfolio Optimization, Trust and Fit Scoring Models, Decision Support Systems, Proposal Compliance AutomationAbstract
Nonprofit organizations face persistent constraints in staff time, proposal capacity, and governance while navigating diverse funder requirements. This paper presents an AI enabled decision intelligence architecture that supports two linked decisions. The first decision is opportunity selection, modeled as a portfolio optimization problem that maximizes expected funding outcomes subject to proposal effort and deadline constraints. The second decision is proposal execution, supported through automated compliance and readability checks plus controlled use of language models for drafting and revision. The architecture integrates a trust and fit scoring model to estimate success likelihood, a narrative quality test suite for requirements and plain language, and a security layer that reduces exposure to phishing and malicious portals in grant communications. We describe an implementation for the adult literacy nonprofit Fill My Cup in Charlotte and define measurable outcomes including win rate, hours to first draft, award size, readability improvements, and reductions in security incident rates. The contribution is a practical blueprint that unifies decision science, portfolio optimization, and applied AI with human oversight to improve grant seeking effectiveness and operational safety.
References
1. Seckel, E., Stephens, B. Y., Rodriguez, F., et al. (2024). Ten simple rules to leverage large language models for getting grants. PLoS Computational Biology, 20(3), e1011863. https://doi.org/10.1371/journal.pcbi.1011863
2. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, Vol. 30, pp. 5998-6008.
3. Qiu, H. S., Peng, H., Fosse, H. B., Woodruff, T. K., & Uzzi, B. (2024). Use of promotional language in grant applications and grant success. JAMA Network Open, 7(12), e2448696. https://doi.org/10.1001/jamanetworkopen.2024.48696
4. Godwin, R. C., DeBerry, J. J., Wagener, B. M., Berkowitz, D. E., & Melvin, R. L. (2024). Grant drafting support with guided generative AI software. SoftwareX, 27, 101784. https://doi.org/10.1016/j.softx.2024.101784
5. Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020). Language (technology) is power: A critical survey of "bias" in NLP. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5454-5476. https://doi.org/10.18653/v1/2020.acl-main.485
6. Kandakoglu, A., et al. (2024). The use of multi criteria decision making in project portfolio selection: A comprehensive literature review. Annals of Operations Research. https://doi.org/10.1007/s10479-023-05564-3
7. Jøsang, A., Ismail, R., & Boyd, C. (2007). A survey of trust and reputation systems for online service provision. Decision Support Systems, 43(2), pp. 618-644. https://doi.org/10.1016/j.dss.2005.05.019
8. Wu, J., & Konstantinidis, S. (2025). A survey on trust and reputation data sharing. arXiv. https://doi.org/10.48550/arXiv.2508.14028
9. Ma, J., Saul, L. K., Savage, S., & Voelker, G. M. (2009). Beyond blacklists: Learning to detect malicious web sites from suspicious URLs. Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1245-1254. https://doi.org/10.1145/1557019.1557153
10. Sahami, M., Dumais, S., Heckerman, D., & Horvitz, E. (1998). A Bayesian approach to filtering junk e-mail. Learning for Text Categorization: Papers from the 1998 Workshop, Vol. 62, pp. 98-105.
11. Sheng, S., Wardman, B., Warner, G., Cranor, L. F., Hong, J., & Zhang, C. (2009). An empirical analysis of phishing blacklists. Proceedings of the Sixth Conference on Email and Anti-Spam (CEAS), Mountain View, CA.
12. Opara, C., Chen, Y., & Wei, B. (2024). Look before you leap: Detecting phishing web pages by exploiting raw URL and HTML characteristics. Expert Systems with Applications, 236, 121183. https://doi.org/10.1016/j.eswa.2023.121183
13. Haq, Q. E. u., Faheem, M. H., & Ahmad, I. (2024). Detecting phishing URLs based on a deep learning approach to prevent cyber-attacks. Applied Sciences, 14(22), 10086. https://doi.org/10.3390/app142210086
14. Schneider, S., et al. (2024). Generative AI governance: An organizational perspective. arXiv. https://doi.org/10.48550/arXiv.2403.08802
15. World Economic Forum. (2024). Governance in the age of generative AI: A 360 approach for resilient governance. World Economic Forum.
16. Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using siamese BERT-networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 3982-3992. https://doi.org/10.18653/v1/D19-1410
17. Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied logistic regression (3rd ed.). John Wiley & Sons. https://doi.org/10.1002/9781118548387
18. Kandakoglu, A., et al. (2024). The use of multi criteria decision making in project portfolio selection: A comprehensive literature review. Annals of Operations Research. https://doi.org/10.1007/s10479-023-05564-3
19. Kincaid, J. P., Fishburne, R. P., Rogers, R. L., & Chissom, B. S. (1975). Derivation of new readability formulas (automated readability index, fog count and flesch reading ease formula) for navy enlisted personnel. Research Branch Report 8-75, Naval Technical Training Command, Millington, TN.
20. Cutts, M. (2020). Oxford guide to plain English (5th ed.). Oxford University Press.
Downloads
Published
Data Availability Statement
Data supporting this study are included within the article.
Issue
Section
License
Copyright (c) 2026 Sai Krishna Gunda (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.