International Journal of
Advanced Multidisciplinary Application

Volume 3, Issue 7

• Author(s)Priyanka S. Wagh, Devendra M. Solanki, Aarti R. Chauhan
• AffiliationDepartment of Computer Science and Engineering, Vivekananda Global University, Jaipur, Rajasthan, India
• Page No.21-27
• Volume, Issue & YearVolume 3, Issue 7, July 2026
• Published On2026/07/01
• JournalInternational Journal of Advanced Multidisciplinary Application (IJAMA)
• ISSN No.3048-9350

Abstract

Post-harvest losses in perishable agricultural commodities constitute one of the most economically consequential and persistently unresolved challenges in Indian agri-food systems, with the National Centre for Cold-chain Development estimating annual losses exceeding 1.53 trillion rupees, driven substantially by information asymmetry between producers and downstream demand, fragmented multi-intermediary distribution chains, and inadequate cold-chain temperature compliance. This study presents an integrated framework combining a permissioned blockchain-based supply chain traceability ledger with a machine learning demand forecasting and demand-supply matching pipeline, piloted across seven perishable commodities (tomato, onion, potato, banana, mango, leafy greens, and grapes) moving through procurement networks linking 240 farmer-producer groups to wholesale mandis and retail outlets in central and western India over an eighteen-month observation period (July 2024-December 2025). The blockchain ledger, implemented on a Hyperledger Fabric permissioned network with IoT-integrated cold-chain temperature logging at five transit stages (farm collection, pack-house, road transit, distribution hub, and retail storage), recorded 184,000 traceability transactions and 62,000 temperature-excursion-monitored shipments, while a Transformer-based temporal demand forecasting model, benchmarked against naive seasonal, ARIMA, Random Forest, and LightGBM baselines, generated mandi-level demand predictions used to drive dynamic demand-supply matching and dispatch scheduling. The blockchain-tracked and ML-optimised supply chain achieved post-harvest loss reductions of 35-45% relative to the traditional multi-intermediary baseline across all seven commodities (e.g., tomato: 28.4% to 17.9%; leafy greens: 34.6% to 21.3%), with road transit identified as the dominant cold-chain temperature excursion stage (18.4 excursions per 100 shipments, mean duration 47 minutes). The Transformer-based forecasting model achieved the best demand prediction accuracy (MAPE=7.4%, R²=0.903), enabling mandi price volatility reductions of 36-45% (coefficient of variation) across commodities. Smart-contract-automated payment settlement reduced farmer payment cycles from a traditional mean of approximately 18 days to under 12 hours, while farmer net price realisation as a share of final consumer price increased from 31.4% to 52.8% through intermediary disintermediation. These findings demonstrate the technical and economic feasibility of integrated blockchain-ML agri-supply-chain infrastructure for simultaneously reducing physical post-harvest losses, dampening price volatility, and improving farmer income realisation in resource-constrained Indian agricultural markets.

Keywords: blockchain, supply chain traceability, machine learning, demand forecasting, post-harvest loss, cold-chain monitoring, smart contracts, agri-food systems, Hyperledger Fabric, farmer income, mandi price volatility

References

1. [1] Agarwal, S., & Steinmetz, R. (2019). Blockchain technology for agriculture supply chains: A systematic literature review
2. on benefits and challenges. Computers and Electronics in Agriculture, 168, 105100.
3. [2] Behera, R. K., Rath, S. K., Mohanty, S. R., & Hota, P. (2021). Smart contracts and Hyperledger Fabric in supply chain
4. traceability systems: Architecture and case studies. Journal of Network and Computer Applications, 178, 102983.
5. [3] Bhattacharya, S., & Bhattacharya, A. (2020). Post-harvest losses in Indian perishable agriculture: An empirical
6. assessment. Agricultural Economics Research Review, 33(1), 45-58.
7. [4] Borade, A. B., & Bansod, S. V. (2007). Domain of supply chain management: A state of art. Journal of Technology
8. Management & Innovation, 2(4), 109-121.
9. [5] Chauhan, C., Parida, V., & Dhir, A. (2022). Linking circular economy and digitalisation technologies: A systematic
10. literature review of past achievements and future promises. Technological Forecasting and Social Change, 177, 121508.
11. [6] Kamble, S. S., Gunasekaran, A., & Sharma, R. (2020). Modeling the blockchain enabled traceability in agriculture supply
12. chain. International Journal of Information Management, 52, 101967.
13. [7] Lim, M. K., Li, Y., Wang, C., & Tseng, M. L. (2021). A literature review of blockchain technology applications in supply
14. chains: A comprehensive analysis of themes, methodologies and industries. Computers & Industrial Engineering, 154,
15. 107133.
16. [8] Ministry of Food Processing Industries. (2023). Annual Report on Post-Harvest Management and Cold Chain
17. Infrastructure in India. Government of India.
18. [9] National Centre for Cold-chain Development. (2022). All India Cold-chain Infrastructure Capacity Assessment Report.
19. Ministry of Agriculture and Farmers Welfare, Government of India.
20. [10] Salah, K., Nizamuddin, N., Jayaraman, R., & Omar, M. (2019). Blockchain-based soybean traceability in agricultural
21. supply chain. IEEE Access, 7, 73295-73305.
22. [11] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017).
23. Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998-6008.
24. [12] Verma, S., & Gustafsson, A. (2020). Investigating the emerging COVID-19 research trends in the field of business and
25. management: A bibliometric analysis approach. Journal of Business Research, 118, 253-261.
26. [13] Zhao, G., Liu, S., Lopez, C., Lu, H., Elgueta, S., Chen, H., & Boshkoska, B. M. (2019). Blockchain technology in agri
27. food value chain management: A synthesis of applications, challenges and future research directions. Computers in Industry,
28. 109, 83-99.

Explore Our Related Journals

Looking for the right journal for your next manuscript? Explore our international peer-reviewed journals covering engineering, management, computer science, artificial intelligence and multidisciplinary research.