Design and Development of a Multi-Agent Artificial Intelligence-Based Financial Planner for Institutional Financial Management Optimization

Intan Dina Kartika; Dwi Soca Baskara; Hardika

doi:10.32664/smatika.v16i01.2167

Authors

Intan Dina Kartika Universitas Negeri Malang
Dwi Soca Baskara Universitas Negeri Malang
Hardika Universitas Negeri Malang

DOI:

https://doi.org/10.32664/smatika.v16i01.2167

Keywords:

Artificial Intelligence, Financial Planning, Retrieval-Augmented Generation

Abstract

Institutional financial management often faces optimization challenges due to limited understanding of influencing factors, difficulties in data integration, and the lack of human expertise. These constraints hinder the identification of opportunities, risk management, and sustainability. An adaptive and automated financial planning system is required. This study proposes the design of an Artificial Intelligence (AI)-based system for automated financial planning aligned with institutional standards. The system addresses these challenges by integrating financial needs analysis, standardized cost references, and automated budget summary preparation. Using a prototyping approach, the system employs AI agents to conduct in-depth analysis and produce comprehensive budgets. The proposed system leverages RAGflow, an open-source Retrieval-Augmented Generation (RAG) engine that uses deep document understanding to provide truthful question-answering from complex data.

References

[1] C. Tian, ‘Research on Financial Management Issues and Countermeasures in Chinese Higher Education Institutions’, Proceedings of Business and Economic Studies, vol. 7, no. 4, Art. no. 4, Aug. 2024, doi: 10.26689/pbes.v7i4.7697.

[2] H. Hong, ‘Optimization Design of Financial Shared Services Based on Improved Algorithms and Artificial Intelligence’, in 2024 3rd International Conference on Data Analytics, Computing and Artificial Intelligence (ICDACAI), Oct. 2024, pp. 552–556. doi: 10.1109/ICDACAI65086.2024.00106.

[3] I. E. Nikulina, E. A. Ershova, A. A. Tarabanovsky, and A. A. Zemtsov, ‘Finance Planning In The University Using Information Methodology “Aris”’, presented at the Information Technologies in Science, Management, Social Sphere and Medicine, Atlantis Press, May 2016, pp. 105–110. doi: 10.2991/itsmssm-16.2016.22.

[4] N. K. D. S. Rahayu and M. A. Meitriana, ‘Pengaruh Literasi Keuangan dan Sikap Keuangan Terhadap Perilaku Pengelolaan Keuangan Mahasiswa Prodi Pendidikan Ekonomi Undiksha’, Ekuitas: Jurnal Pendidikan Ekonomi, vol. 11, no. 2, Art. no. 2, 2023, doi: 10.23887/ekuitas.v11i2.65999.

[5] I. Irmawati and S. Aprilia, ‘Ketidaksesuaian Realisasi Belanja Pemeliharaan Dengan Rencana Anggaran Menjadi Permasalahan Pembiayaan Di Sekolah’, Jurnal Penelitian Pendidikan, vol. 24, no. 2, pp. 221–226, Aug. 2024, doi: 10.17509/jpp.v24i2.73372.

[6] R. Ramlall and S. Grobbelaar, ‘Deficiencies in the traditional budgeting process cause the negative behaviour of budgetary slacking’, South African Journal of Business Management, vol. 55, no. 1, p. 12, Jun. 2024, doi: 10.4102/sajbm.v55i1.4348.

[7] J. Febriantoko, Sistem Informasi Akuntansi. 2024.

[8] F. Zamzami, N. D. Nusa, and I. A. Faiz, Sistem Informasi Akuntansi. UGM PRESS, 2021.

[9] F. B. Limba and S. G. Sapulette, SISTEM INFORMASI AKUNTANSI. CV WIDINA MEDIA UTAMA, 2023. Accessed: Jun. 29, 2025. [Online]. Available: https://repository.penerbitwidina.com/publications/564573/

[10] A. Amirkhani and A. H. Barshooi, ‘Consensus in multi-agent systems: a review’, Artif Intell Rev, vol. 55, no. 5, pp. 3897–3935, Jun. 2022, doi: 10.1007/s10462-021-10097-x.

[11] R. Calegari, G. Ciatto, V. Mascardi, and A. Omicini, ‘Logic-based technologies for multi-agent systems: a systematic literature review’, Auton Agent Multi-Agent Syst, vol. 35, no. 1, p. 1, Oct. 2020, doi: 10.1007/s10458-020-09478-3.

[12] R. C. Cardoso and A. Ferrando, ‘A Review of Agent-Based Programming for Multi-Agent Systems’, Computers, vol. 10, no. 2, Art. no. 2, Feb. 2021, doi: 10.3390/computers10020016.

[13] J. Palanca, A. Terrasa, V. Julian, and C. Carrascosa, ‘SPADE 3: Supporting the New Generation of Multi-Agent Systems’, IEEE Access, vol. 8, pp. 182537–182549, 2020, doi: 10.1109/ACCESS.2020.3027357.

[14] J. D. Naumann and A. M. Jenkins, ‘Prototyping: The New Paradigm for Systems Development’, MIS Quarterly, vol. 6, no. 3, pp. 29–44, 1982, doi: 10.2307/248654.

[15] R. Budde, K. Kautz, K. Kuhlenkamp, and H. Züllighoven, Prototyping: An Approach to Evolutionary System Development. Springer Science & Business Media, 2012.

[16] S. Cho, J. Moon, J. Bae, J. Kang, and S. Lee, ‘A Framework for Understanding Unstructured Financial Documents Using RPA and Multimodal Approach’, Electronics, vol. 12, no. 4, p. 939, Jan. 2023, doi: 10.3390/electronics12040939.

[17] S. Kim, H. Song, H. Seo, and H. Kim, ‘Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems’, Mar. 19, 2025, arXiv: arXiv:2503.15191. doi: 10.48550/arXiv.2503.15191.

[18] C. Aldemir and T. Uçma Uysal, ‘Artificial Intelligence for Financial Accountability and Governance in the Public Sector: Strategic Opportunities and Challenges’, Administrative Sciences, vol. 15, no. 2, p. 58, Feb. 2025, doi: 10.3390/admsci15020058.

[19] N. Ammar and A. Shaban-Nejad, ‘Explainable artificial intelligence recommendation system by leveraging the semantics of adverse childhood experiences: Proof-of-concept prototype development’, JMIR Medical Informatics, vol. 8, no. 11, 2020, doi: 10.2196/18752.

[20] A. Roy, J. Ara, S. Ghodke, and J. Akter, ‘Artificial Intelligence in Corporate Financial Strategy: Transforming Long-Term Investment and Capital Budgeting Decisions’, Journal of Economics, Finance and Accounting Studies, vol. 7, no. 5, pp. 50–59, Sep. 2025, doi: 10.32996/jefas.2025.7.5.6.

[21] S. Zhao, Z. Jin, S. Li, and J. Gao, ‘FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain’, Sep. 09, 2025, arXiv: arXiv:2505.17471. doi: 10.48550/arXiv.2505.17471.

[22] K. B. P. Y. Perkasa and F. E. Purwiantono, ‘Sistem Rekomendasi Jurusan Menggunakan Algoritma NaÃ¯ve Bayes Gaussian Berbasis Web’, J-INTECH, vol. 11, no. 2, pp. 361–370, Dec. 2023, doi: 10.32664/j-intech.v11i2.1090.