AI-DRIVEN MODEL FOR ECONOMIC EFFICIENCY IN SOFTWARE DEVELOPMENT TASKS
DOI:
https://doi.org/10.68302/std2026.vol1.177Keywords:
Artificial Intelligence, Economic Effectiveness, Two core AI modelAbstract
The use of Artificial Intelligence (AI) has become an inseparable part of the software development process, parts of which are routine, requiring precision rather than creativity. AI code generation speeds up productivity by automatically completing code fragments and frees up time and brainpower to perform more tasks that require creativity or problem-solving. When writing code, the programmer uses not only the accumulated experience, but often also intuition, which helps him assess both the correctness of the code and the implications of its use.
At the same time, AI uses different and increasingly sophisticated models and a thought chain resembling human thinking through modern approaches to Large Language Models (LLM) and Neural Networks. However, increasingly serious problems are emerging when using AI.
The publication proposes a model of an AI algorithm with two functionally different cores: one creative and one process, including control functions. This model overcomes a large part of the identified shortcomings of AI and complements their development. The model is supplemented with quantitative metrics to determine the economic efficiency of its application.
Supporting Agencies
The research is funded by the National Science Fund of Bulgaria under the project KP-06-N55/3 on the topic “Conceptual Model for Evaluation of Fast-Growing Companies Operating in Innovation-Intensive Industries Based on Artificial Intelligence Methods”.Downloads
References
[1] J. Revuri, R. K. Sakthivel, G. Nagasubramanian, Chapter Five - Artificial intelligence (AI) technologies and tools for accelerated software development, Editor(s): Pethuru Raj, Mats Agerstam, Pushan Kumar Dutta, B. Sundaravadivazhagan, Gayathri Nagasubramanian, Advances in Computers, Elsevier, Volume 141, 2026, Pages 115-159, ISSN 0065-2458, ISBN 9780443224010, https://doi.org/10.1016/bs.adcom.2025.07.001.
[2] E. De La Cruz, H. Le, K. Meduri, G. S. Nadella, H. Gonaygunta, Redefining the Programmer: Human-AI Collaboration, LLMs, and Security in Modern Software Engineering, Computers, Materials and Continua, Volume 85, Issue 2, 2025, Pages 3569-3582, ISSN 1546-2218, https://doi.org/10.32604/cmc.2025.068137.
[3] K. S. Kumari, B. Sundaravadivazhagan, V. Indumathy, D. Maladhy, Chapter Seven - Detailing AI techniques and tools for software engineering acceleration and automation, Editor(s): Pethuru Raj, Mats Agerstam, Pushan Kumar Dutta, B. Sundaravadivazhagan, Gayathri Nagasubramanian, Advances in Computers, Elsevier, Volume 141, 2026, Pages 183-209, ISSN 0065-2458, ISBN 9780443224010, https://doi.org/10.1016/bs.adcom.2025.07.007.
[4] K. Adnyana, A. Schwung, Benchmarking and validation of prompting techniques for AI-assisted industrial PLC programming, Machine Learning with Applications, Volume 23, 2026, 100804, ISSN 2666-8270, https://doi.org/10.1016/j.mlwa.2025.100804.
[5] L. Banh, F. Holldack, G. Strobel, Copiloting the future: How generative AI transforms Software Engineering, Information and Software Technology, Volume 183, 2025, 107751, ISSN 0950-5849, https://doi.org/10.1016/j.infsof.2025.107751.
[6] F. A. Bañuls-Lapuerta, V. Marti-Miralles, R. J. Gónzalez-García, G. Martínez-Rico, Using Natural Language Prompts With AI Models for Low-Cost Assistive Software Design: Exploratory Comparative Evaluation, JMIR Rehabilitation and Assistive Technologies, Volume 13, 2026, ISSN 2369-2529, https://doi.org/10.2196/86786.
[7] B. Czarnacka-Chrobot, AI applications in software functional size measurement: A systematic literature review, Journal of Systems and Software, Volume 232, 2026, 112686, ISSN 0164-1212, https://doi.org/10.1016/j.jss.2025.112686.
[8] M. Esposito, X. Li, S. Moreschini, N. Ahmad, T. Cerny, K. Vaidhyanathan, V. Lenarduzzi, D. Taibi, Generative AI for software architecture. Applications, challenges, and future directions, Journal of Systems and Software, Volume 231, 2026, 112607, ISSN 0164-1212, https://doi.org/10.1016/j.jss.2025.112607.
[9] M. Glas, C. Nirschl, B. Lanyado, J. van Niekerk, Insecure by design? A human-centric security perspective on AI-assisted software development, Computers & Security, Volume 164, 2026, 104842, ISSN 0167-4048, https://doi.org/10.1016/j.cose.2026.104842.
[10] H. A. Al-Hashimi, R. A. Khan, H. S. Alwageed, A. M. Algarni, S. Ayouni, A. O. Almagrabi, Exploring the role of generative AI in enhancing cybersecurity in software development life cycle, Array, Volume 28, 2025, 100509, ISSN 2590-0056, https://doi.org/10.1016/j.array.2025.100509.
[11] N. Basheer, S. Islam, P. Kumar, D. Javeed, N. Islam, A responsible AI-driven framework for robust and transparent software vulnerability detection, Information and Software Technology, Volume 195, 2026, 108126, ISSN 0950-5849, https://doi.org/10.1016/j.infsof.2026.108126.
[12] D. Shao, F. Ishengoma, Empirical analysis of generative AI tool adoption in software development, Information and Software Technology, Volume 192, 2026, 108036, ISSN 0950-5849, https://doi.org/10.1016/j.infsof.2026.108036.
[13] A. Ampatzoglou, E.-M. Arvanitou, S. Almpanopoulos, N. Mittas, A. Chatzigeorgiou, AI-assisted code refactoring: Where can it be helpful and where do humans outperform it?, Journal of Systems and Software, Volume 238, 2026, 112862, ISSN 0164-1212, https://doi.org/10.1016/j.jss.2026.112862.
[14] G. Giray, A software engineering perspective on engineering machine learning systems: State of the art and challenges, Journal of Systems and Software, Volume 180, 2021, 111031, ISSN 0164-1212, https://doi.org/10.1016/j.jss.2021.111031.
[15] K. Anguelov, "Applications of Artificial Intelligence for Optimization of Business Processes in Enterprise Resource Planning Systems," 2021 12th National Conference with International Participation (ELECTRONICA), Sofia, Bulgaria, 2021, pp. 1-4, doi: 10.1109/ELECTRONICA52725.2021.9513677
[16] K. Anguelov, "AI-Based Predictive Model for High-Growth Enterprises," 2025 13th International Scientific Conference on Computer Science (COMSCI), Sozopol, Bulgaria, 2025, pp. 1-5, doi: 10.1109/COMSCI67172.2025.11225285.
[17] Z. Fang, Y. Yuan, J. Zhang, Y. Liu, Y. Mu, Q. Lu, X. Xu, J. Wang, Ch. Wang, Sh. Zhang, Sh. Chen, MLOps Spanning Whole Machine Learning Life Cycle: A Survey, arXiv, arXiv:2304.07296, 2023, https://doi.org/10.48550/arXiv.2304.07296.
[18] N. Sambasivan, Sh. Kapania, H. Highfill, D. Akrong, Pr. Paritosh, L.M. Aroyo, “Everyone wants to do the model work, not the data work”: Data Cascades in High-Stakes AI, CHI '21: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, Article No.: 39, Pages 1 – 15, 2021, NY, USA, ISBN 9781450380966, https://doi.org/10.1145/3411764.3445518.
[19] D. Zha, Z. P. Bhat, K. Lai, F. Yang, Zh. Jiang, Sh. Zhong, X. Hu, Data-centric Artificial Intelligence: A Survey, arXiv, arXiv:2303.10158, 2023, https://doi.org/10.48550/arXiv.2303.10158.
[20] N. Polyzotis, S. Roy, St. E. Whang, M. Zinkevich, Data Lifecycle Challenges in Production Machine Learning: A Survey, Association for Computing Machinery, SIGMOD Rec. Volume 47, 2018, ISSN 0163-5808, https://doi.org/10.1145/3299887.3299891.
[21] H. Naveed, Ch. Arora, H. Khalajzadeh, J. Grundy, O. Haggag, Model driven engineering for machine learning components: A systematic literature review, Information and Software Technology, Volume 169, 2024, 107423, ISSN 0950-5849, https://doi.org/10.1016/j.infsof.2024.107423.
[22] Ch. Janiesch, P. Zschech, K. Heinrich, (2021). Machine learning and deep learning. 10.48550/arXiv.2104.05314, https://doi.org/10.1007/s12525-021-00475-2.
[23] Y. Watanabe, H. Washizaki, K. Sakamoto, D. Saito, K. Honda, N. Tsuda, Y. Fukazawa, N. Yoshioka, (2019). Preliminary Systematic Literature Review of Machine Learning System Development Process. 10.48550/arXiv.1910.05528, https://doi.org/10.48550/arXiv.1910.05528.
[24] O. Bousquet, A. Elisseeff, (2002). Stability and Generalization. Journal of Machine Learning Research. 2. 499-526. 10.1162/153244302760200704.
[25] B. Neal, S. Mittal, A. Baratin, V. Tantia, M. Scicluna, S. Lacoste-Julien, I. Mitliagkas, (2018). A Modern Take on the Bias-Variance Tradeoff in Neural Networks. 10.48550/arXiv.1810.08591, https://doi.org/10.48550/arXiv.1810.08591.
[26] R. M. Freund, Introduction to Optimization, and Optimality Conditions for Unconstrained Problems, Massachusetts Institute of Technology, OpenCourseWare, 2004, https://ocw.mit.edu/courses/15-084j-nonlinear-programming-spring-2004/f8e5bd09d99cc296e0f5af25bf607e49_lec1_unconstr_opt.pdf
[27] R.L. Carraway, T.L. Morin, Theory and applications of generalized dynamic programming: An overview, Computers & Mathematics with Applications, Volume 16, Issues 10–11, 1988, Pages 779-788, ISSN 0898-1221, https://doi.org/10.1016/0898-1221(88)90188-5.
[28] Sh. A. Licorish, A. Bajpai, Ch. Arora, F. Wang, K. Tantithamthavorn, Comparing Human and LLM Generated Code: The Jury is Still Out!, arXiv, arXiv:2501.16857, 2025, https://doi.org/10.48550/arXiv.2501.16857
[29] Y. Liu, R. Widyasari, Y. Zhao, I. Cl. Irsan, D. Lo, Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild, arXiv, arXiv.2603.28592, 2026, ttps://doi.org/10.48550/arXiv.2603.28592.
[30] N. Nascimento, P. Alencar, D. Cowan, Comparing Software Developers with ChatGPT: An Empirical Investigation, arXiv, arXiv:2305.11837, 2023, https://doi.org/10.48550/arXiv.2305.11837
[31] R. Petrov, Mikroprotsesorni sistemi i mikrokontroleri: Uchebno pomagalo za zadalzitelna podgotovka v profesionalnite gimnazii s napravlenie „Elektronika i avtomatizatsiya“. Sofia: Novi znaniya, 2011, ISBN 978-954-2907-04-6
[32] Luchkov, K., & Velinova-Sokolova, N. (2026). Methodology for Quantitative Risk Assessment in the Integration and Use of ERP Systems in Enterprises. Journal of Risk and Financial Management, 19(3), 226. https://doi.org/10.3390/jrfm19030226
[33] Luchkov, K., Chipriyanova, G., Chipriyanov, M. (2025). Implementing Innovative Strategies for Competitiveness in the Era of Digital Transformation. In: Alzoubi, H.M., Cheng Ling, T., El Khatib, M. (eds) Innovative Dynamics in Management and Engineering (IDME) . ISCME 2024. Advances in Science, Technology & Innovation. Springer, Cham. https://doi.org/10.1007/978-3-031-90131-7_29
[34] Chipriyanova, G., Chipriyanov, M., Luchkov, K. (2024). Investigation and Analysis of Attitudes Towards the Implementation of Artificial Intelligence in Internal Business Processes. In: Proceedings of the 15th International Scientific and Practical Conference “Environment, Technology and Resources”, Rezekne, 2024, Vol. II, pp. 61–67. https://doi.org/10.17770/etr2024vol2.8032
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Viktor Hristov, Miglena Angelova
This work is licensed under a Creative Commons Attribution 4.0 International License.
