Detailed Analysis of Automating Detention Claim Approval in Shipping with AI Agents and LLMs |
||
 |
 |
|
| © 2025 by IJCTT Journal | ||
| Volume-73 Issue-5 |
||
| Year of Publication : 2025 | ||
| Authors : Mukesh Kumar | ||
| DOI : 10.14445/22312803/IJCTT-V73I5P118 | ||
How to Cite?
Mukesh Kumar, "Detailed Analysis of Automating Detention Claim Approval in Shipping with AI Agents and LLMs," International Journal of Computer Trends and Technology, vol. 73, no. 5, pp. 144-154, 2025. Crossref, https://doi.org/10.14445/22312803/IJCTT-V73I5P118
Abstract
In the $1 trillion shipping industry, approving detention claims where drivers wait additional hours for loading or unloading requires plant and logistics managers to manually match in/out timings from Transportation Management Systems (TMS) with Proofs of Delivery (PODs) and driver tracking details, taking 1–2 days per claim (Transport Topics, 2023). This paper explores how AI agents powered by Large Language Models (LLMs) can automate this process, reducing approval times to 5–30 minutes, a 90–95% efficiency gain. By integrating with TMS, parsing PODs with 90% accuracy (McKinsey, 2024), and analyzing textual data to determine fault (e.g., carrier lateness vs. shipper delays), these agents approve or deny claims like $100 for a 2-hour wait in real-time.
For 100 monthly claims, this saves 100–200 days of effort annually, cutting labour costs by $7,500–$15,000 at $75/hour (Cass Freight Index, 2023). In this automated landscape, shippers process claims instantly, reducing disputes by 15% (FreightWaves, 2024) and improving carrier relations, though 6–12 month integration timelines and 5–10% data inaccuracies pose challenges (Gartner, 2024). This transformation promises a faster, more consistent detention approval process in a high-stakes logistics ecosystem.
Keywords
AI agents, LLMs, Detention approval, Shipping logistics, TMS integration, document parsing, Automation efficiency.
Reference
[1] Surendra Mohan Devaraj, “AI and Cloud for Claims Processing Automation in Property and Casualty Insurance,” International Journal of Engineering and Technology Research, vol. 8, no. 1, pp. 38-46, 2023.
[CrossRef] [Google Scholar]
[2] Md. Syful Islam, “Navigating Modern Era at Sea: Legal Challenges and Opportunities of Unmanned and Autonomous Shipping,” AI and Ethics, vol. 5, pp. 2293-2306, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Suraj Dharmasastha, “Intelligent Transformation of Logistics Hub with Automated Transportation by Integrating Blockchain Technology,” TU Delft, Master Thesis, 2021.
[Google Scholar]
[4] David Freeman Engstrom et al., “Government by Algorithm: Artificial Intelligence in Federal Administrative Agencies,” NYU School of Law, Public Law Research Paper, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Mehran Farzadmehr, “AI-powered Solutions Assessment in Port and Maritime Sector,” University of Antwerp, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] A. Shaji George, and A.S. Hovan George, “Towards a Super Smart Society 5.0: Opportunities and Challenges of Integrating Emerging Technologies for Social Innovation,” Partners Universal International Research Journal, vol. 3, no. 2, pp. 1-29, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Muhammad Usman Hadi et al., “A Survey on Large Language Models: Applications, Challenges, Limitations, and Practical Usage,” Authorea Preprints, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Ramesh Chandra Aditya Komperla, “AI-enhanced Claims Processing: Streamlining Insurance Operations,” Journal of Research Administration, vol. 3, no. 2, pp. 95-106, 2021.
[Google Scholar]
[9] Wolfgang Lehmacher, “Digitizing and Automating Processes in Logistics,” Disrupting Logistics, pp. 9-27, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Svjetlana Maksimović et al., “New EU Regulation of Autonomous Artificial Intelligence: Implications, Effects, and Industry Development,” University of Ljubljana Repository, 2024.
[Google Scholar] [Publisher Link]
[11] Wengang Mao, and Simon Larsson, Increase Shipping Efficiency using Ship Data Analytics and AI to Assist Ship Operations, 2023.
[Google Scholar] [Publisher Link]
[12] Bernard Marr, Artificial Intelligence in Practice: How 50 Successful Companies used AI and Machine Learning to Solve Problems, John Wiley & Sons, 2019.
[Google Scholar] [Publisher Link]
[13] Chris Medeiros, “The Rise of Artificial Intelligence and the Importance of Media Literacy: Decoding AI-generated News,” Communication Honors Theses, 2025.
[Google Scholar] [Publisher Link]
[14] Tymoteusz Miller et al., “Leveraging Large Language Models for Enhancing Safety in Maritime Operations,” Applied Sciences, vol. 15, no. 3, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Joel Niklaus, “Decoding Legalese without Borders: Multilingual Evaluation of Language Models on Long Legal Texts,” University of Bern, 2024.
[Google Scholar] [Publisher Link]
[16] Frank Poon, “Improving Logistics using Smart Technology,” Smart Manufacturing: The Lean Six Sigma Way, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Fotis Sarantopoulos, “Decarbonizing the Shipping Industry through Innovative Technologies, Artificial Intelligence and New Regulations,” Massachusetts Institute of Technology, 2024.
[Google Scholar] [Publisher Link]
[18] Meera Sharma, “Legal Rights in Artificial Intelligence,” Sarvalokum: Law and Society Multidisciplinary National Peer-Reviewed Journal, vol. 2, no. 1, pp. 147-159, 2025.
[Google Scholar] [Publisher Link]
[19] Ishana Shastri, “Automating Accountability Mechanisms in the Judiciary System using Large Language Models,” Massachusetts Institute of Technology, 2024.
[Google Scholar] [Publisher Link]
[20] Igor Tovstolis, “Methods and Approaches to Integrating Innovative Technologies in 3PL Provider Management: From Automation to Artificial Intelligence,” iBusiness, vol. 16, no. 4, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Robekka Vuohelainen, “Artificial Intelligence (AI) and Robotic Process Automation (RPA) in the Insurance Business,” Theseus, 2024.
[Google Scholar] [Publisher Link]
[22] Lukas Ryll et al., “Transforming Paradigms: A Global AI in Financial Services Survey,” SSRN, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Stawomir Wyciślak, and Pourya Pourhejazy, “Supply Chain Control Tower and The Adoption of Intelligent Dock Booking for Improving Efficiency,” Frontiers in Energy Research, vol. 11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Yuan Zhang et al., “Dynamic Insights: Unraveling Public Demand Evolution in Health Emergencies through Integrated Language Models and Spatial-temporal Analysis,” Risk Management and Healthcare Policy, vol. 17, pp. 2443-2455, 2024.
[Google Scholar] [Publisher Link]
[25] Peter Stone et al., “Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligence,” arXiv preprint arXiv:2211.06318, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Marcia Narine Weldon, Gabrielle Thomas, and Lauren Skidmore, “Establishing a Future-proof Framework for AI Regulation: Balancing Ethics, Transparency, and Innovation,” Transactions: The Tennessee Journal of Business Law, vol. 25, 2024.
[Google Scholar] [Publisher Link]
[27] Sam J. Tangredi, and George Galdorisi, AI at War: How Big Data, Artificial Intelligence, and Machine Learning are Changing Naval Warfare, Naval Institute Press, 2021.
[Google Scholar] [Publisher Link]
[28] Ikhtiyor B. Djuraev et al., “The Impact of Digitization on Legal Systems in Developing Countries,” Qubahan Academic Journal, vol. 5, no. 1, pp. 81-117, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Rosario Girasa, “Applications of AI and Projections of AI Impact,” Artificial Intelligence as a Disruptive Technology, pp. 23-67, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Vinay Katari et al., “A Confluence of Emerging Technologies Like IoT, Edge & Cloud Computing, Blockchain, Industry 4.0 & 5.0, AI & ML toward the Realization of Eco-friendly Supercapacitors,” Eco-friendly Supercapacitors: Design and Future Perspectives in Sustainable and Green Energy Storage Devices, pp. 163-204, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Olalekan Hamed Olayinka, “Ethical Implications and Governance of AI Models in Business Analytics and Data Science Applications,” International Journal of Engineering and Technology Research Management, vol. 6, no. 11, 2022.
[Google Scholar]
[32] Ardi Janjeva et al., “The Rapid Rise of Generative AI: Assessing Risks to Safety and Security,” Centre of Emerging Technology and Security, 2023.
[Google Scholar] [Publisher Link]
[33] Neel Guha et al., “AI Regulation has its Own Alignment Problem: The Technical and Institutional Feasibility of Disclosure, Registration, Licensing, and Auditing,” George Washington Law Review, vol. 92, no. 6, 2024.
[Google Scholar] [Publisher Link]
[34] Balagopal Ramdurai, “Large Language Models (LLMs), Retrieval-augmented Generation (RAG) Systems, and Convolutional Neural Networks (CNNs) in Application Systems,” International Journal of Marketing and Technology, vol. 15, no. 1, 2025.
[Google Scholar]