https://doi.org/10.62660/bcstu/4.2025.97

Volume 30, No. 4, 2025

97-106

  • Read article

    • Comparison of simple algorithms and artificial intelligence in the development of a personal asset tracking service

    Pavlo Kozolup

    Received 01.08.2025, Revised 14.11.2025, Accepted 15.12.2025

    Abstract

    Analysis of modern scientific literature reveals a tendency towards the widespread implementation of artificial intelligence, often without sufficient consideration of indirect efficiency factors such as economic costs, implementation complexity, maintenance, and information security. These studies focus more on the accuracy and performance metrics of artificial intelligence systems, while ignoring indirect but critically important efficiency factors. The aim of this article was to investigate the suitability of applying Artificial Intelligence technologies compared to simple algorithmic solutions within the context of developing software applications for personal asset management. The research methodology was based on a comprehensive comparative analysis of a developed simple algorithm for predicting the time of the next product order and the statistical Auto Regressive Integrated Moving Average (ARIMA) model, as a representative of more complex, albeit not deep, intelligent methods for time series forecasting. Based on the implementation and experiment using data that simulated a real-world scenario, the performance of both approaches was evaluated using key metrics, including accuracy, required computational resources, and implementation complexity. It was found that for tasks with limited data volumes and relatively simple behavioral patterns, which are characteristic of small personal asset management projects, the simple algorithm demonstrated comparable accuracy to the artificial intelligence ARIMA model. It was revealed that the simple algorithm operated with lower computational costs, measured in nanoseconds, and was characterised by lower implementation and subsequent maintenance complexity. The analysis showed that the use of ARIMA, despite its statistical power, was less justified under such conditions, requiring greater computational expenditures and deeper knowledge for its configuration. It was demonstrated that the execution time of ARIMA on small samples was higher (in microseconds), and its reliability was significantly dependent on the volume and quality of the input data. Thus, the necessity of a reasoned choice of technologies, based on the real needs and resource constraints of the project, was emphasised

    Keywords:

    machine learning; software development; forecasting; efficiency; personalisation

    Suggested citation
    Kozolup, P. (2025). Comparison of simple algorithms and artificial intelligence in the development of a personal asset tracking service. Bulletin of Cherkasy State Technological University, 30(4), 97-106. https://doi.org/10.62660/bcstu/4.2025.97
    348 Views

    References

    1. Anderljung, M., Hazell, J., & von Knebel, M. (2025). Protecting society from AI misuse: When are restrictions on capabilities warranted? AI & Society, 40, 3841-3857. doi: 10.1007/s00146-024-02130-8.
    2. Ashurst, C., Barocas, S., Campbell, R., & Raji, D.D. (2022). Discovering the components of ethical research in machine learning. In Proceedings of the FAccT ‘22: 2022 ACM conference on fairness, accountability, and transparency (pp. 2057-2068). New York: ACM. doi: 10.1145/3531146.3533781.
    3. Brundage, M., et al. (2020). Toward trustworthy AI development: Mechanisms for supporting verifiable claims. ArXiv. doi: 10.48550/ARXIV.2004.07213.
    4. Chafik, N., & Benchekroun, D.A. (2020). Integrating artificial intelligence in software engineering: Enhancements and challenges in the development lifecycle. International Research Journal of Engineering and Technology, 7(6), 1184-1188.
    5. Dilmaghani, S., Brust, M.R., Danoy, G., Cassagnes, N., Pecero, J., & Bouvry, P. (2019). Privacy and security of big data in AI systems: A research and standards perspective. In 2019 IEEE international conference on big data (big data) (pp. 5737-5743). Los Angeles: IEEE. doi: 10.1109/BigData47090.2019.9006283.
    6. He, J., et al. (2023). Control risk for potential misuse of artificial intelligence in science. ArXiv. doi: 10.48550/ arXiv.2312.06632.
    7. Islam, M.Z., Gurung, N., Gazi, M.S., & Hasan, M.R. (2024). Novel AI-powered dynamic inventory management algorithm in the USA: Machine learning dimension. Journal of Economic, Financial and Administrative Sciences, 6(2), 156-168. doi: 10.32996/jefas.2024.6.2.12.
    8. Javadi, S.A., Cloete, R., Cobbe, J., Lee, M.S.A., & Singh, J. (2020). Monitoring misuse for accountable “artificial intelligence as a service”. In AIES ‘20: Proceedings of the AAAI/ACM conference on AI, ethics, and society (pp. 300-306). New York: ACM. doi: 10.1145/3375627.3375873.
    9. Kozolup, P., & Liubchak, V. (2024a). Functional model and algorithm for the development of an information service for accounting and procurement of goods. Technical Sciences and Technologies, 2(36), 116-125. doi: 10.25140/2411-5363-2024-2(36)-116-125.
    10. Kozolup, P., & Liubchak, V. (2024b). Review of methods and tools for the development of an information service for personal asset. Information Technology and Society, 3(9), 47-53. doi: 10.32689/maup.it.2023.3.6.
    11. Lins, S., Pandl, K.D., Teigeler, H., Gimpel, G., Hirt, R., & Klesse, M. (2021). Artificial intelligence as a service. Business & Information Systems Engineering, 63, 441-456. doi: 10.1007/s12599-021-00708-w.
    12. Menard, P., & Bott, G.J. (2024). Artificial intelligence misuse and concern for information privacy: New construct validation and future directions. Information Systems Journal, 34(4), 1146-1182. doi: 10.1111/isj.12544.
    13. Pöhler, L., Schrader, V., Ladwein, A., & von Keller, F. (2024). A technological perspective on misuse of available AI. ArXiv. doi: 10.48550/arXiv.2403.15325.
    14. Raximov, N., Primqulov, O., & Daminova, B. (2021). Basic concepts and stages of research development on artificial intelligence. In International conference on information science and communications technologies (ICISCT) (pp. 1-4). Tashkent: IEEE. doi: 10.1109/ICISCT52966.2021.9670085.
    15. Rodriguez, D., et al. (2023). Leveraging generative AI tools to support the development of digital solutions in health care research. JMIR Human Factors, 11, article number e52885. doi: 10.2196/52885.
    16. Sarker, I.H. (2022). AI-based modeling: Techniques, applications and research issues towards automation, intelligent and smart systems. SN Computer Science, 3, article number 158. doi: 10.1007/s42979-022-01043-x.
    17. Shapovalova, N., Dotsenko, I., Trachuk, A., & Skrynnikov, I. (2024). Application of artificial intelligence tools for time series analysis. Journal of Kryvyi Rih National University, 22(1), 46-51. doi: 10.31721/2306-5451-2024-158-46-52.
    18. Tominc, P., Oreški, D., Čančer, V., & Rožman, M. (2024). Statistically significant differences in AI support levels for project management between SMEs and large enterprises. AI, 5(1), 136-157. doi: 10.3390/ai5010008.
    19. Valavanidis, A. (2023). Artificial intelligence (AI) applications. Retrieved from https://www.researchgate.net/ publication/369914014.
    20. Van Zuylen, H. (2012). Difference between artificial intelligence and traditional methods. In Artificial intelligence applications to critical transportation issues (pp. 3-5). Washington: Transportation Research Board.
    21. Veluru, C.S. (2024). Responsible artificial intelligence on large scale data to prevent misuse, unethical challenges and security breaches. Journal of Artificial Intelligence & Cloud Computing, 3(2), 1-6. doi: 10.47363/ JAICC/2024(3)331.