SmartPack: AI-Powered Box Size Packaging Optimization Platform for SMEs and MSMEs

Abstract

Packaging inefficiency is a common challenge for Small and Medium Enterprises (SMEs) and Micro, Small, and Medium Enterprises (MSMEs), where box sizes are often selected through manual estimation, leading to poor space utilization, higher transportation costs, and increased material waste. This paper presents SmartPack, a cloud-based packaging optimization platform designed to improve box size selection and packaging efficiency through structured computational analysis. The system analyzes product dimensions such as length, width, height, and weight, and compares them with predefined box configurations to recommend the most suitable packaging option. In addition, the platform incorporates digital twin–based three-dimensional visualization to simulate product placement within the recommended box before actual packaging. The system also evaluates packaging cost and space utilization to support data-driven decision making. Experimental results indicate significant improvements in packaging performance, with space utilization increasing from approximately 65% to nearly 85–90% and packaging costs reduced by around 15–25%. These findings demonstrate that SmartPack provides an efficient and scalable solution for intelligent packaging optimization, helping SMEs and MSMEs reduce operational costs, improve logistics efficiency, and promote sustainable packaging practices.

Introduction

Packaging significantly impacts supply chain efficiency, product protection, costs, and sustainability. Small and medium enterprises (SMEs) and micro, small, and medium enterprises (MSMEs) often rely on manual estimation for packaging, leading to oversized cartons, wasted materials, higher shipping costs, and environmental inefficiency. Unlike large enterprises, SMEs lack accessible, data-driven tools for optimized packaging decisions.

Objective:
SmartPack is a web-based, cloud platform developed to optimize packaging for SMEs and MSMEs. It recommends box sizes, evaluates material usage, visualizes product placement through digital twins, and calculates cost savings to improve efficiency and sustainability.

Key Features and Modules:

1. Sustainability & Material Selection: Allows selection of packaging strategies (cost-driven, balanced, or eco-friendly) and evaluates corrugated board types for strength and feasibility.

2. Box Size Optimization: Compares product dimensions with available box sizes to maximize space utilization and reduce void space.

3. Digital Twin Simulation: Provides 3D visualization of product placement to validate packaging feasibility and reduce trial-and-error adjustments.

4. Cost Evaluation: Estimates packaging expenditure and compares manual versus optimized configurations to quantify savings.

5. Integration & Interface: Supports ERP and warehouse system integration with a user-friendly web interface for simple data entry, visualization, and reporting.

Methodology:

• Secure authentication and role-based access control

• Structured product data acquisition and validation

• Volume and space utilization analysis

• Optimization engine selects best-fit box

• Digital twin simulation for verification

• Packaging cost evaluation and dashboard reporting

Results:

• Optimized packaging reduced void space from ~45% to 10–15%

• Space utilization improved from ~65% to 85–90%

• Packaging costs decreased by 15–25% compared to manual methods

• System response times were fast (1–2 seconds), and historical reporting was stable

Conclusion

This study introduced SmartPack, a packaging optimization platform developed to enhance box size selection, improve space utilization, and reduce packaging costs for SMEs and MSMEs. The proposed system combines volume-based evaluation techniques, packaging cost analysis, and digital twin visualization to support structured and data-driven packaging decisions. The evaluation results demonstrate notable improvements in packaging efficiency. Space utilization increased from approximately 65% under conventional packaging practices to nearly 85–90% using the optimized approach. Additionally, packaging expenses were reduced by about 15–25%, indicating clear economic benefits. The system also delivers recommendations in real time while maintaining low computational complexity. Overall, the SmartPack platform provides a practical and scalable solution for intelligent packaging optimization. By improving packaging efficiency and reducing material waste, the system supports more cost-effective and sustainable logistics operations for SMEs and MSMEs.

References

[1] K. S. Gurumoorthy and A. Hinge, “A decision-tree framework to select optimal box-sizes for product shipments,” arXiv preprint arXiv:2202.04277, 2022. doi:10.48550/arXiv.2202.04277. [2] X. Li, D. Liu, Y. Pu, and Y. Zhong, “Recent advance of intelligent packaging aided by artificial intelligence for monitoring food freshness,” Foods, vol. 12, no. 15, p. 2976, 2023. doi: 10.3390/foods12152976. [3] E. Peretz-Andersson, S. Tabares, P. Mikalef, and V. Parida, “Artificial intelligence implementation in manufacturing SMEs: A resource orchestration approach,” International Journal of Information Management, vol. 77, p. 102781, 2024. doi: 10.1016/j.ijinfomgt.2024.102781. [4] S. K. Verma, S. Sonika, D. K. Ram, A. Shukla, and V. Kumar, “Smart solutions: AI and sustainable packaging – A mini review,” African Journal of Biomedical Research, vol. 27, no. 4S, pp. 954–960, 2024. [5] H. Zghair and R. G. Konathala, “Using AI for optimizing packing design and reducing cost in e-commerce,” AI, vol. 6, no. 7, p. 146, 2025. doi: 10.3390/ai6070146. [6] L. Kumar, R. Dutt, and K. K. Gaikwad, “Packaging 4.0: Artificial intelligence and machine learning applications in the food packaging industry,” Current Food Science and Technology Reports, vol. 3, p. 19, 2025. doi: 10.1007/s43555-025-00064-w. [7] A. A. Dandge, “Rise and use of artificial intelligence and machine learning in packaging processes of e-commerce giant Amazon pre and post Covid,” International Journal of Advanced Research in Science, Communication and Technology, vol. 5, no. 12, pp. 100–106, 2025. [8] M. M. Alper, B. Sezen, and Y. S. Balc?o?lu, “Machine learning applications in packaging industry optimization: A systematic literature review and future research directions,” in Proc. International New York Academic Research Congress, 2025. [9] Y. Ma, Y. Zhou, Q. Fang, S. Xia, and W. Chen, “A three-dimensional container loading algorithm for solving logistics packing problem,” EURO Journal on Transportation and Logistics, vol. 14, p. 100167, 2025. doi: 10.1016/j.ejtl.2025.100167. [10] M. B. Yel, N. A. Multazam, and Y. Gunawan, “Optimization of SME inventory systems through the application of AI-based predictive technology,” Journal of Social Science and Education Research, vol. 3, no. 1, pp. 52–60, 2026.

Copyright

Copyright © 2026 Prof. Mr. Gargey M. Aware, Nitin U. Kingar, Aniket M. Khatkhede, Nishikant S. Nachane, Anurag D. Dhawane. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.