Application of ai driven system for estimation of orders in the printing industry
Abstract
Printing enterprises face growing competition, rapid tech progress, and higher demands for efficiency and quality. In this context, fast and accurate order evaluation is essential for resource optimization, cost reduction, and competitiveness. Traditional methods − manual input, expert judgment, and classic financial models − are labor-intensive, inflexible, and poorly suited to today’s diverse technologies.
Intelligent information systems offer significant value by automating data analysis, revealing hidden patterns, and supporting informed decisionmaking. Their use streamlines production, lowers costs, and boosts financial performance.
Although many printing stages (prepress, color management, quality control) are automated, smart order estimation remains underdeveloped − creating bottlenecks, especially for small and medium print runs.
This article presents the adaptation of the Flex Estimate AI system for the printing industry. Initially designed for IT project evaluation, the system was enhanced with machine learning and data mining to deliver automated, transparent, and accurate order assessment. Its adoption improves planning, optimizes workflows, and strengthens business resilience during digital transformation.
Downloads
References
2. Star product: Heidelberg Prinect Touch Free. (n.d.). Printweek. Retrieved April 28, 2025, from https://www.printweek.com/content/features/starproduct-heidelberg-prinect-touch-free/.
3. Nagorny P., & Baziuk D. (2023). Otsinka finansovogo stanu iak peredumova efektivnogo upravleniya pidpriyemstvo. Transformation economics, (1(01)), 44-49. https://doi.org/10.32782/2786-8141/2023-1-8
4. Kostaryev D. B., Tevyashev A. D., Sizova N. D., & Tkachenko V. P. (2024). Analysis of the problem of forecasting in proactive enterprise management. In Intelligent Sustainable Systems. Selected Papers of WorldS4 2023, Volume 1 (pp. 539-549). Springer. https://doi.org/10.1007/978-981- 99-8031-4
5. Bagan, T. G. (2021). Methods of machine learning in the design of automated control systems [Electronic resource]. Kyiv: KPI im. Igor Sikorskyi. https://ela.kpi.ua/handle/123456789/45676
6. Makatiora A., Makatiora D., Zenkin M., & Kubanov R. (2024). Information and communicative technologies as a tool for improving the efficiency of economic activity of polygraphic printing enterprises. Herald of Khmelnytskyi National University. Economic Sciences, 334(5), 97-105. https://doi.org/10.31891/2307-5740-2024-334-14
7. Kostaryev D.B. Pearson V., Dovgiy, D. V. Tkachenko V. F., & Tevyashev A. D. (2024). Application of AI technologies to optimize project estimation processes in IT companies. In Proceedings of the International scientific and technical conference (pp. 144-150). Kharkiv: Kharkiv: KNURE. https://openarchive.nure.ua/server/api/core/bitstreams/c325d86f-3d29- 4f73-873e-ec91628dbc17/content
Copyright (c) 2025 D. Kostaryev, V. Tkachenko, N. Sizova

This work is licensed under a Creative Commons Attribution 4.0 International License.