Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68552
Volume:
10 |
10 |
Oct 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Artificial Intelligence and Machine Learning
Zeal Polytechnic, Pune

Artificial Intelligence and Machine Learning
Zeal Polytechnic, Pune

Artificial Intelligence and Machine Learning
Zeal Polytechnic, Pune

Artificial Intelligence and Machine Learning
Zeal Polytechnic, Pune

Artificial Intelligence and Machine Learning
Zeal Polytechnic, Pune

Artificial Intelligence and Machine Learning
Zeal Polytechnic, Pune
Agricultural trading faces challenges such as dependence on intermediaries, price uncertainty, limited market access, and difficulties in verifying crop quality. To address these issues, this paper proposes AgriConnect, an AI- and blockchain-based smart agricultural marketplace that connects farmers and buyers directly. The platform enables farmers to list crops and buyers to purchase products, compare prices, and communicate through voice calls, video calls, or a chatbot. A Convolutional Neural Network (CNN) is proposed to detect visible crop quality defects using freshly captured images through the application's camera, without allowing gallery uploads for quality analysis. Random Forest Regression will estimate crop prices using historical market data and relevant crop, date, and location features, enabling comparisons between selected agricultural markets. Blockchain technology and smart contracts will support transparent digital agreements and tamper-evident transaction records. Product images and other large files will be stored off-chain where appropriate, while relevant verification hashes and transaction references may be recorded on-chain. The proposed system will be evaluated using precision, recall, F1-score, and a confusion matrix for quality classification, and Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R² for price prediction. AgriConnect aims to improve agricultural market transparency, support informed purchasing decisions, and reduce unnecessary intermediaries through the integration of artificial intelligence, direct communication, location-based price estimation, and blockchain technology. Actual system performance will be established through implementation and experimental testing.
KEYWORDS
AgriConnect proposes an integrated agricultural marketplace that combines artificial intelligence, location-based price estimation, direct farmer–buyer communication, and blockchain technology. CNN-based image classification can support the assessment of visible crop quality defects, while Random Forest Regression can estimate crop prices using historical market data. Smart contracts can support transparent digital agreements and tamper-evident transaction records. The platform aims to improve market accessibility and help farmers and buyers make informed decisions. Its effectiveness must be established through implementation, testing, and quantitative evaluation. Future work may include expanding crop image datasets, improving model performance, integrating verified real-time market price feeds, strengthening multilingual chatbot support, and conducting field trials with farmers and buyers.
[1] Y. Cao, C. Yi, G. Wan, H. Hu, Q. Li, and S. Wang, “An analysis on the role of blockchain-based platforms in agricultural supply chains,” Transportation Research Part E: Logistics and Transportation Review, vol. 163, Art. no. 102731, 2022, doi: 10.1016/j.tre.2022.102731. [2] G. H. Harish Nayak et al., “Exogenous variable driven deep learning models for improved price forecasting of TOP crops in India,” Scientific Reports, vol. 14, Art. no. 17203, 2024, doi: 10.1038/s41598-024-68040- 3. [3] L. E. Chuquimarca, B. X. Vintimilla, and S. A. Velastin, “A review of external quality inspection for fruit grading using CNN models,” Artificial Intelligence in Agriculture, vol. 14, pp. 1–20, 2024. DOI: 10.1016/j.aiia.2024.10.002
Publication Date
10/31/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
3
Total views since publication
PDF Downloads
7
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...